Reaction network flux analysis: Optimization‐based evaluation of reaction pathways for biorenewables processing

Even though biomass is attracting increasing interest as a raw material in the chemical and the fuel industries, only few biobased production processes are yet established. At the same time a lot of new catalytic routes are proposed, but their potential in biorefinery applications is hard to predict. Reaction network flux analysis (RNFA) is introduced as a novel, rapid screening method which bridges the gap between chemo‐ or biocatalysis and process design by (1) systematically identifying and (2) subsequently analyzing and ranking the large number of alternative reaction pathways based on limited data. This optimization‐based method helps to detect promising production routes as well as bottlenecks in possible pathways. The potential and the application of the RNFA methodology will be demonstrated by means of a case study for the production of the potential biofuel 3‐methyl‐tetrahydrofuran (3‐MTHF) from the platform chemical itaconic acid (IA). © 2011 American Institute of Chemical Engineers AIChE J, 58: 1788–1801, 2012     

基于PCA-BP神经网络的精馏塔产品组成软测量模型

通过共轭梯度算法和BP神经网络对精馏过程进行软测量建模.依据工艺原理和经验知识,初选了精馏塔顶产品组成的神经网络输入变量,运用主元分析法对变量进行主元分解,降低了变量维数,并且消除了变量之间的相关性,最后对网络进行了训练与测试.仿真结果表明,该模型具有较快的收敛速度,较高的精度,可以满足大规模生产诊断的要求.     

煤种成浆性的人工神经网络预测模型研究

为更好地预测煤的成浆性,以大量煤种成浆浓度试验数据为基础,建立了3个输出因子的神经网络成浆浓度预测模型,模型采用L-M算法,对输入数据进行数据预处理,最后对比分析了神经网络预测模型与回归分析模型的预测结果。结果表明,以A_d、哈氏可磨性指数HGI和氧含量O为输入因子的模型预测结果平均绝对误差为0.63%,以M_(ad)、HGI和O为输入因子的模型预测结果平均绝对误差为0.60%,以M_(ad)、HGI和氧碳比O/C为输入因子的模型预测结果平均绝对误差为0.40%,3种组合的模型结果均小于回归分析模型的平均绝对误差1.15%。因此神经网络模型比回归分析模型有更好的预测能力,其中以M_(ad)、HGI和O/C为输入因子的神经网络模型预测结果最好。     

Folding rate prediction based on neural network model

One of the most important challenges in biology is to understand the relationship between the folded structure of a protein and its primary amino acid sequence. A related and challenging task is to understand the relationship between sequences and folding rates of proteins. Previous studies found that one of contact order (CO), long-range order (LRO), and total contact distance (TCD) has a significant correlation with folding rate of protein. Although the predicted results from TCD can provide better results, the deviation is also large for some proteins. In this paper, we adopt back-propagation neural network to study the relationship between folding rate and protein structure. In our model, the input nodes are CO, LRO, and TCD, and the output node is folding rate. The number of nodes in the hidden layer is seven. Our results show that the relative errors for the predicted results are even lower than other methods in the literature. We also observe a best excellent correlation between the folding rate and contact parameters (including CO, LRO, and TCD), and find that the folding rate depends on CO, LRO and TCD simultaneously. This means that CO, LRO and TCD are similarly important in folding rate of protein. Some comparisons are made with other methods.     

基于WOA-BP算法的持液率预测模型研究

湿气管道在运行过程中,不可避免地会在管道低洼处出现积液.积液的存在会诱发很多安全问题,严重时甚至引发事故.因此,对湿气管道持液率进行预测就显得至关重要.文中基于灰色理论,对影响水平管道持液率的6个影响因素进行灰色关联分析,选取影响较大的因素作为影响变量;基于鲸鱼算法,建立鲸鱼算法优化BP神经网络的持液率预测模型,并与传...     

A macroscopic model for shear-thinning flow in packed beds based on network modeling

The flow of non-Newtonian fluids in packed beds and other porous media is important in several applications such as polymer processing, filtration, and enhanced oil recovery. Expressions for flowrate versus pressure gradient are desirable for a-priori prediction and for substitution into continuum models. In this work, physically representative network models are used to model the flow of shear-thinning fluids, including power-law and Ellis fluids. The networks are used to investigate the effects of fluid rheology and bed morphology on flow.A simple macroscopic model is developed for the flow of power-law and Ellis fluids in packed beds using results from the network model. The model has the same general functionality as those developed using the popular bundle-of-tubes approach. The constant β, which appears in these models, is often directly derived from the tortuosity and a simple representation of the porous media. It is shown here that this can lead to incorrect and ambiguous values of the constant. Furthermore, the constant is a weak function of the shear-thinning index, indicating that no single bundle-of-tubes could ever properly model flow for a wide variety of shear-thinning fluids.The macroscopic model is compared to experimental data for shear-thinning fluids available in the literature. The model fits the data well when β is treated as an experimental parameter. The best-fit values of β vary, which is expected because even the constant C in the Blake-Kozeny equation varies depending on the source consulted. Additionally, physical effects, such as adsorption and filtration, as well as rheological effects such as viscoelasticity may affect the value of β. We believe that in the absence of these effects, β equals approximately 1.46 for packed beds of uniform spheres at relatively moderate values of the shear-thinning index (>0.3).     

A method of model validation for chaotic chemical reaction systems based on neural network

A chaotic system with measurable state variables fewer than the degrees of freedom of the system is identified with the Artificial Neural Network (ANN) method combined with dynamic training. Instead of using the usual method of Sum of Square Errors (SSE), the identified models are validated with the return maps (embedded trajectories), the largest Lyapunov exponent, and the correlation dimension when there is no exogenous input, and bifurcation diagram when there is an exogenous input. This method is demonstrated for nonisothermal, irreversible, first-order, series reaction A→ B → C in a CSTR.     

基于BP网络的保护渣性能预测模型的研究

结合BP网络计算机实验研究 ,建立了保护渣化学组成与性能的预测模型 ,并利用化学组成与性能的关系 ,对网络的实用性进行了检验 ,结果符合保护渣化学组成与性能的关系。保护渣粘度随着保护渣碱度的增大而减小 ,而半球点温度随碱度增大而增大 ;保护渣的半球点温度和粘度都随着渣中CaF2 含量的增加而减小。用BP网络的误差反向传播算法建立的保护渣的化学组成与性能的预测模型 ,得出的预测值与实际值的误差小 ,对保护渣的设计与应用都有一定的指导作用。     

基于RBF网络的胶磷矿浮选精矿指标预测模型

本文基于RBF神经网络构造了云南某胶磷矿浮选多因素输入和浮选精矿品位、回收率之间的浮选模型,并在Matlab环境下进行了计算机仿真试验,结果表明,模型预测精度较高,验证了非参数建模的合理性,具有一定的实用价值,为浮选过程的控制奠定了基础.     

基于径向基函数神经网络的挤出温度预测模型

简要介绍了软测量方法建立挤出温度预测模型的方法,分析其优缺点后进而提出应用基于RBF神经网络建立渝度预测模型,试验后对比了实测值和预测值,结果表明该方法能达到较好的预测精度,同时具有使用简洁、快速等优点,具有较好的应用推广意义。     

基于BP神经网络的结晶成核速率预测

利用神经网络所具有的输入输出之间的高度非线性映射关系,给出了一种利用BP神经网络模型预测磷酸二氢铵结晶成核速率的方法。在对网络进行训练的基础上,建立了磷酸二氢铵结晶生长速率与过饱和度、冷却温度、饱和温度及悬浮密度和之间的数学模型。仿真结果表明,利用文中所提出的神经网络模型能够较准确、快速地预测结晶成核速率的变化,预测值与测量值的最大相对误差不超过5.9%,表明该网络预测模型有很大的实用性。     

基于粗糙集和RBF神经网络的风电场短期风速预测模型

结合粗糙集提出了一种RBF神经网络短期风速预测模型。采用粗糙集对预测模型的输入特征空间进行约简,找出对未来预测的风速具有主要影响的因素,以此作为RBF神经网络预测模型的输入变量;在RBF神经网络训练的过程中,采用在线滚动优化策略,将最新的样本加入训练集,从而使预测模型能够跟踪风速的最新变化。将提出的方法用于某风电场的1 h短期风速预测,仿真实验结果表明该方法具有结构简单、预测精度高的优点。     

A simple approach for protein structure discrimination based on the network pattern of conserved hydrophobic residues

Evolutionarily conserved hydrophobic residues at the core of protein structures are generally assumed to play a structural role in protein folding and stability. Recent studies have implicated that their importance to protein structures is uneven, with a few of them being crucial and the rest of them being secondary. In this work, we explored the possibility of employing this feature of native structures for discriminating non-native structures from native ones. First, we developed a network tool to quantitatively measure the structural contributions of individual amino acid residues. We systematically applied this method to diverse fold-type sets of native proteins. It was confirmed that this method could grasp the essential structural features of native proteins. Next, we applied it to a number of decoy sets of proteins. The results indicate that such an approach indeed identified non-native structures in most test cases. This finding should be of help for the investigation of the fundamental problem of protein structure prediction.     

重组枯草芽孢杆菌生产青霉素G酰化酶发酵条件的研究

对产青霉素G酰化酶的温度诱导型重组枯草芽孢杆菌发酵条件进行了研究。结果表明,培养基的最佳氮源和碳源组成为:35gL-1牛肉膏、3gL-1葡萄糖和6gL-1淀粉;最佳诱导时机是细胞对数生长的中后期,诱导前应将pH调节至中性;最佳诱导条件为升高温度至50℃并维持4min;随后将温度降低到34℃进行重组蛋白的表达。在上述条件下,PGA的表达水平可以达到5.8UmL-1。SDS-PAGE电泳分析表明该重组菌能够将绝大部分表达的PGA分泌到细胞外,而且表达的PGA蛋白占有高比例(90%)。     

A predictive neural network model based on the karhunen-loéave expansion for wall-cooled fixed-bed reactors

Experiments were carried out with a pilot scale, wall cooled, fixed-bed reactor for benzen oxidation. The inlet concentration of benzene was varied in three ways: periodically, with PRBS, and by means of a step change. A model for the reactor is developed with use of the Karhunen-Loéve (K-L) expansion and neural networks. The K-L expansion procedure used here acts as a preprocessor to achieve good data compression while preserving as much information about the measurements as possible. A recurrent multilayer feedforward network is then used to relate the coefficients of the K-L expansion to the operating conditions. The model developed is used for on-line prediction of the axial temperatures in a fixed-bed reactor and results show that the predictions are in good agreement with measurements.     

The control of MSF desalination plants based on inverse model control by neural network

In this paper, a nonlinear inverse model control strategy based on neural network is proposed for MSF desalination plant. Artificial neural networks (ANNs) can handle complex and nonlinear process relationships, and are robust to noisy data. The designed neural networks consist of three layers identified from input–output data and trained with a descent gradient algorithm. The set point tracking performance of the proposed method was studied when the disturbance is present in the MSF system. Three controllers are designed for controlling the top brine temperature, the level of last stage and salinity. These results show that a neural network inverse model control strategy (NNINVMC) is robust and highly promising to be implemented in such nonlinear systems. Also the comparison between the top brine temperature of the proposed model and NN predicted data from the literature supports the accuracy of the model.     

基于神经网络模型预测涤纶FDY油剂及其乳液的外观

将基础油剂、偏亲水乳化剂和偏亲油乳化剂按不同配比制备涤纶全拉伸丝(FDY)油剂以及油剂质量分数为1%的乳液,定量分析油剂及乳液的外观随基础油剂含量、偏亲水乳化剂含量的变化规律;建立以基础油剂含量及偏亲水乳化剂含量为输入、油剂及乳液的外观为输出的分类神经网络模型,用采集的不同配方下油剂及乳液的外观进行网络训练,用新配方下油剂及乳液的外观进行模型验证。结果表明:油剂及乳液的外观是关于基础油剂含量、偏亲水乳化剂含量的分段函数,在基础油剂含量确定时,随着偏亲水乳化剂含量增加,油剂及乳液的外观依次呈现出白色乳液、略带蓝光白色乳液、蓝白色半透明液体、透明液体和暗灰色液体,且油剂分层;分类神经网络模型经训练后,准确率达98.3%,模型拟合效果好,能准确预测新配方下油剂及乳液的外观,可以为判断新油剂配方下能否制备微乳液体系提供帮助。     

基于ARMA模型和趋势分析的铁谱定量参数分析与预测

在自行搭建的齿轮箱磨损实验平台的基础上,获取了38组代表齿轮磨损程度的铁谱直读读数,并以此为基础介绍了处理该数据的ARMA模型理论及趋势分析方法。通过对二者原理及优缺点的分析提出了将ARMA模型理论和趋势分析方法组合的数据处理方法。利用该方法对获取的数据进行分析:对前35组数据进行时序建模并获取后3组数据的预测值,并利用趋势分析法将获取的监测值与预测值进行对比比较。结果表明:该组合分析方法在对设备磨损值的预测及磨损状态的判定和预测方面具有较好的精度,可作为一种新的数据处理方式运用到实际的设备故障监测工作中。     

E-12环氧树脂生产新工艺技术经济分析

介绍了Ｅ－１２环氧树脂生产技术概况，对５００ｔ／ａＥ－１２环氧树脂生产新工艺进行了技术经济分析。     

基于主成分分析的煤元素分析通用预测模型研究

基于大量煤质分析数据,以主成分分析法对煤的发热量和工业分析数据进行预处理,应用三元线性回归和BP网络分析研究主成分与煤的各元素间的关系,进而提出了煤元素分析通用预测模型,并对模型适应性进行了检验;结果表明所建模型具有较强的适应性。