混沌遗传算法估计反应动力学参数

为了准确地估计反应动力学参数 ,提出一种混沌遗传算法 (chaosgeneticalgorithm ,CGA) ,它基于混沌变量的遗传操作 ,将使子代个体均匀地分布于定义空间 ,从而可避免早熟 ,以较大的概率实现全局最优搜索 .与传统的遗传算法相比较 ,CGA的在线和离线性能都有较大的改进 .将CGA应用于 2 -氯苯酚在超临界水中氧化反应动力学参数的估算 ,获得了满意的结果     

多样性分布参数的粒子群算法及其在过程动态优化中的应用

提出一种多样性分布参数的粒子群算法(DDPPSO)。在DDPPSO算法中,每个粒子在初始化时拥有各自的惯性权重和加速因子。在迭代时由每个粒子的寻优性能决定其参数的权重,进而计算参数群体的加权平均值。根据加权平均值与自适应方差,通过正态分布产生下一代参数个体,从而实现参数群体的多样性分布,为算法的寻优提供实时最佳的控制参数。标准测试函数实验表明,在寻优性能上DDPPSO算法较新改进的PSO算法有较大提高。最后,将DDPPSO算法应用于Park-Ramirez生物反应器的动态优化,获得满意的结果。     

基于改进最大相关最小冗余的选择性集成分类器

在构建选择性集成分类器时,寻找分类准确率高且差异性大的最优分类器子集至关重要.为平衡集成子集中基分类器的准确性和多样性,提出了一种基于改进最大相关最小冗余的选择性集成分类器(ImRMRSEC).首先,将基分类器对验证集的预测结果视为一个个"特征",把特征选择的思想扩展到集成分类器的约简问题中,基于最大相关最小冗余准则寻...     

基于MLFN-PLSR的PX氧化反应组合建模方法

针对对二甲苯（p-xylene，PX）氧化反应过程中影响主要副产物对羧基苯甲醛（4-carboxybenzaldehyde，4-CBA）含量的因素众多且呈高度非线性的特征，提出了多层前向型神经网络（multi-layer feedforward network，MLFN）与偏最小二乘回归（partial least squares regression，PLSR）相结合的建模方法，建立反应产物中4-CBA含量关联模型。MLFN-PLSR采用三层网络结构和尽量多的隐节点，通过MLFN充分提取样本数据信息；然后采用PLSR消除隐含层输出冗余信息，建立具有良好预测精度的模型。与MLFN相比，最佳性能模型的预测偏差平方和均值下降了12.11%、模型平均预测偏差平方和均值下降了8.37%。与PLSR相比，最佳性能模型的预测偏差平方和均值下降了70.62%。     

基于PCA-ANN组合学习方法建立PTA粒度模型

针对在精对苯二甲酸(PTA)生产过程中影响PTA粒度的因素多且复杂，采用了主元分析方法(PCA)提取方差最大的几个成分作为神经网络(ANN)的输入，消除干扰因素的影响，建立PCA-ANN粒度模型。为了进一步提高PCA-ANN粒度模型的预测精度，提出了性能优良的加权组合学习方法，形成基于PCA-ANN的加权组合模型。组合模型能通过对多个不同PCA-ANN粒度模型的预测结果进行自适应加权。最终获得具有良好预测精度的结果。     

模糊自适应遗传算法及其在化工中的应用

Considering that the performance of a genetic algorithm (GA) is affected by many factors and their rela-tionships are complex and hard to be described,a novel fuzzy-based adaptive genetic algorithm (FAGA) combined a new artificial immune system with fuzzy system theory is proposed due to the fact fuzzy theory can describe high complex problems.In FAGA,immune theory is used to improve the performance of selection operation.And,crossover probability and mutation probability are adjusted dynamically by fuzzy inferences,which are developed according to the heuristic fuzzy relationship between algorithm performances and control parameters.The experi-ments show that FAGA can efficiently overcome shortcomings of GA,i.e.,premature and slow,and obtain better results than two typical fuzzy GAs.Finally,FAGA was used for the parameters estimation of reaction kinetics model and the satisfactory result was obtained.     

Production of fructose-1, 6-diphosphate (FDP) by permeabilized saccharomyces cerevisiae and a kinetic model for FDP accumulation

Permeable yeast cells were used in the batch production of fructose-1,6-diphosphate(FDP).The optimum reaction conditions were reported to be:reaction temperature 30℃,tolueneconcentration 8%(V/V),and initial ratio of glucose to inorganic phosphorus(Pi)10:1.Addition ofAMP was found to be very beneficial to the FDP production.A multienzyme system model for FDPaccumulation was developed,in which FDP was regarded as a substrate of phosphor-fructokinase(PFK),to simulate the activation effect of FDP on PFK.The model simulations were in good agree-ment with the experimental data.     

KPCA-RVM组合建模方法及其在软测量中的应用

提出了一种核主元分析(KPCA)和关联向量机(RVM)相结合的组合建模方法。KPCA - RVM采用KPCA对原始自变量进行非线性变换并提取主成分,形成特征自变量;采用 RVM,对 KPCA变换后的样本数据进行回归建模,并根据模型的预报能力自适应的确定参与回归的最佳特征变量个数,消除冗余信息干扰,获得强非线性表达能力且预报性能良好的模型。并将KPCA - RVM应用于 PTA装置对羧基苯甲醛(4 - CBA)含量的软测量建模,结果表明该方法预测精度高于PCA - RVM和RVM。     

Fault diagnosis and process monitoring using a statistical pattern framework based on a self-organizing map

A multivariate method for fault diagnosis and process monitoring is proposed. This technique is based on a statistical pattern(SP) framework integrated with a self-organizing map(SOM). An SP-based SOM is used as a classifier to distinguish various states on the output map, which can visually monitor abnormal states. A case study of the Tennessee Eastman(TE) process is presented to demonstrate the fault diagnosis and process monitoring performance of the proposed method. Results show that the SP-based SOM method is a visual tool for real-time monitoring and fault diagnosis that can be used in complex chemical processes.Compared with other SOM-based methods, the proposed method can more efficiently monitor and diagnose faults.