基于模拟分析技术和随机搜索算法的化工过程能量集成方法研究

夹点和模拟分析技术已在化工能量集成中广泛应用.今以夹点技术为基础,对化工过程系统用能进行诊断,根据"过程用能一致性"原则提出能量集成改造方案,通过改变塔压实现塔顶冷凝器与塔底再沸器的热集成多效蒸馏.夹点技术实现的优化目标仅是热回收最大或公用工程能耗最小,不能实现包括设备整体费用最小的过程全局最优化.研究基于模拟技术,通过灵敏度分析,得到精馏塔各操作参数的样本映射数据,通过多项式拟合得到参数关联方程,并在遗传算法及模式搜索中设计过程费用函数,提出了将模拟分析技术与随机搜索算法相结合的,以过程费用函数最小化为优化目标的能量集成方法.工业实例的成功设计应用证明了其有效性和可行性.     

基于SDNA-GA 优化的模糊神经网络控制

针对最新的生物DNA研究,病毒中同一DNA碱基顺序可以编码出2条或者3条不同的多肽链.在此基础上分析与模仿了重叠基因和重叠密码的机理,得到一种新的基于重叠基因编码框架,从而提高了问题求解的效率;同时,得到一种移码解读框架的DNA遗传算法(SDNA-GA)计算模型,并将其应用于一类广义隶属度型T-S模糊神经网络控制器(GTS-FNNC)的优化设计,实现了GTS-FNNC的在线学习.     

一种基于随机GA的提高BP网络泛化能力的方法

LM-BP网络对其初始权值和阈值敏感,泛化能力不强,针对该缺点,采用遗传算法（GA）对其初始权阈值进行优化,在一定程度上能提高LM-BP网络的泛化能力。为进一步扩展GA初始种群的覆盖范围,进一步提高LM—BP网络的泛化能力,采用多次随机产生初始种群多次优化的方法。以伦河孝感段氟化物含量为实例,建立随机GA的LM—BP网络模型,对原始数据进行拟合及测试,结果表明该方法基本能100％拟合,测试误差不超过2．3％。经过对比实验,证明了该方法的有效性。     

MULTIVARIATE WALSH-FOURIER ANALYSIS

Abstract. In this paper we establish a statistical methodology for the spectral analysis of stationary multivariate time series via the Walsh-Fourier transform. Theoretical results pertaining to the definition and estimation of the Walsh-Fourier spectral matrix and functions of that matrix including cross-spectra, coherency and phase are given. An example of the statistical techniques developed in this paper is given; in particular, the methodologies are applied to neonatal sleep data collected from a study of the effect of maternal substance use during pregnancy.     

Flow pattern measurement in a full scale silo containing iron ore

The flow pattern in a silo is important because it affects both the recovery of solids and the pressures on the silo wall during discharge. Wherever mass flow is not achieved, the boundary of the flow channel has significant implications for both the functional and structural design of the silo. Many techniques have been used for the study of flow patterns in model silos, but most cannot be used at full scale, and very few quality measurements at full scale have ever been made. This paper outlines a full scale experimental study in which the patterns of solids flow and the flow channel boundaries are reliably quantified.The full scale silo was specially designed, constructed and instrumented to exhibit funnel flow and to make observations of the solids flow pattern and the silo wall pressures. It had three outlets: one concentric, one fully eccentric and one in between. Three materials were used: iron ore pellets, slag fines and crushed basalt. This paper describes experiments involving iron ore pellets. The silo was seeded with radio frequency tags whose residence times were measured by detecting them on exit during discharge. The residence time data were studied to deduce the discharge flow pattern. This paper presents the results of three different flow pattern interpretation techniques: the best of them (mass-time relationships) is shown to give a very clear identification of the solids flow pattern and the flow channel boundary.     

AlON-TiN复相材料的合成及工艺优化

在对Ti—Al-O-N体系热力学分析的基础上合成了AlON—TiN复相材料，XRD，TEM分析与观测结果证实了热力学分析的可靠性。运用人工神经元网络(artificial neural networks，ANN)对合成AlON—TiN的工艺参数进行了训练，训练结果良好，神经网络的预测值和实测值一致；遗传算法(genetic algorithm，GA)寻优得到最佳工艺参数：烧结温度为1830℃，保温2．45h，TiN的含量为15％(质量分数)。对遗传算法寻优结果进行了单因素分析，随着TiN含量的增加，强度增加，而随烧结温度和保温时间的增加，强度先增加后减小。     

基于神经网络的丙烯腈流化床反应器的离线模拟与优化

A mathematical model is developed for an industrial acrylonitrile fluidized-bed reactor based on artificial neural networks.A new algorithm,which combines the characteristics of both genetic algorithm(GA) and generalized delta-rule(GDR) is used to train artificial neural network (ANN) in order to avoid search terminated at a local optimal solution.For searching the global optimum,a new algorithm called SM-GA,incorporating advantages of both simplex method (SM) and GA, is proposed and applied to optimize the operating conditions of an acrylonitrile fluidized-bed reactor in industry.     

实数编码量子共生演算法及其在云任务调度中的应用

针对共生演算法收敛慢和易陷入局部最优的问题,结合量子遗传算法理论,提出一种实数编码的量子共生演算法(real-coded quantum symbiotic organisms search,RQSOS)。首先依据三角模糊数提出差异度概念,并依此构造一个以自变量向量的分量和一对概率幅为等位基因的三倍染色体,使一条染色体携带更多信息并增强解的多样性;然后提出一种基于阿基米德螺旋线的探索学习模式,加强对解空间的探索精度;最后使用共生演算法更新差异度值并依据差异度值对种群进行学习和变异操作,促使整个种群快速向最优方向进化且减小了陷入局部最优的概率。利用数值优化问题和云任务调度问题对算法进行验证,仿真结果表明,RQSOS算法在收敛速度和寻优能力上均有明显提升,是一种可行有效的算法。     

云制造环境下面向多目标优化的虚拟资源调度研究

为解决云制造环境下虚拟资源调度存在的算法求解效率不高、模型建立缺乏考虑任务间关系约束和任务间及子任务间的物流时间及成本因素等不足,构建了兼顾交货期时间最小化、服务成本最低化、服务质量最优化为目标的多目标虚拟资源调度模型;采用一种基于项目阶段的双链编码方式进行编码,并提出自适应交叉与变异概率公式,以避免交叉、变异概率始终不变导致算法效率下降与过早收敛的问题;在此基础上利用基于项目阶段的多种交叉变异策略相结合的改进遗传算法进行求解,保证了算法的全局与局部搜索性能。实例结果表明,相比于传统的模型与算法,该模型适用性更强,改进的遗传算法在求解效率、准确度与稳定性方面均有较大提高。     

基于改进自适应遗传算法的移动WSN覆盖方法

针对传统的WSN覆盖模型的弊端,尤其是如果一个传感器失效,K-覆盖模型需要至少k个传感器节点监测其范围内是否有目标需要覆盖,提出了一种基于改进自适应遗传算法的移动WSN覆盖方法,在能量资源有限的前提下,尽可能长时间的对指定的目标进行连续监测。该算法考虑到了移动传感器是可以连续和变速运动的,从而能够保证所有目标都在它们的覆盖范围内。仿真结果表明,在使用移动节点的情况下,与其他常用模型相比,改进方法的生存周期和数据包数量都有明显提高。