模糊神经网络在CO_2汽提塔液位预测中的研究

二氧化碳汽提塔液位系统是一个复杂非线性过程,本文基于一种新型复合型模糊神经网络,对该液位系统的建模和预测进行了研究。仿真实验表明,该网络在复杂非线性过程中具有较好的性能,为实现模糊神经网络在化工生产过程中的应用提供了思路和方法。     

与机理杂交的支持向量机为发酵过程建模

针对生物发酵过程机理复杂、高度非线性的特点,采用基于结构风险最小的支持向量机为发酵过程建模,其算法规范,建模复杂度低于神经网络方法,所建模型的预测效果更好.还将生化过程的动力学机理与支持向量机相结合,采用串联和串并联结构,提出与机理杂交的支持向量机建模方法,并为间歇式酒精发酵过程中酵母菌体浓度变化建立了预测模型.原理分析与试验结果表明与机理杂交的支持向量机建模方法,相比于单一近似的动力学模型、单一的支持向量机模型,以及机理杂交的神经网络模型,它的预测精度高,泛化能力强,性能更为优越.     

基于改进粒子群算法的汽油辛烷值损失优化

针对调和汽油辛烷值建模中的变量选择问题、模型适应性问题与辛烷值的优化问题,采用随机森林、最大信息系数与皮尔森相关系数组合提出了一种辛烷值建模变量选择的方法.还提出一种基于BP神经网络与模糊神经网络的建模方法,建立对辛烷值的预测模型,提高了辛烷值预测模型的适应性.在此基础上,对基本粒子群算法进行了改进,改进后的粒子群算法...     

流程模拟中不精确模块的模糊建模

将模糊集合理论与常规建模方法相结合,提出了采用经验规则对不精确单元建模的方法,研究了模糊关系模型的输入输出信息的界面问题,将模糊关系模型运用于工厂过程模拟。结果表明,充分利用专家知识和操作经验,采用人工智能的方法可以处理那结机理比较复杂而难以用常规方法模拟分析的过程系统单元,扩展了过程系统模拟的功能和范围。     

机器学习预测叶片-网孔管线式高剪切混合器性能

高剪切混合器作为一种新型的过程强化设备,工业应用 日益广泛,但其工程设计依然依靠经验放大.利用不同定转子构型的叶片-网孔管线式高剪切混合器的功耗、液-液传质系数和乳化性能等数据,采用反向传播神经网络算法、循环神经网络算法和决策树算法等机器学习算法对数据进行分析建模,为高剪切混合器的设计与优化提供工具.结果表明:反向传播...     

基于自适应学习速率的模糊神经网络控制器

针对模糊神经网络控制器中很难确定一个最佳学习速率的问题,将带有动量因子的自适应学习速率BP算法引入模糊神经网络控制器中。采用模糊推理自适应调节学习速率,同时引入动量因子,提高系统的收敛速度,并基于Lyapunov定理给出了系统稳定的证明过程。针对同一数学模型,用Matlab编程仿真3种方法的实验结果表明:优化后的模糊神经网络控制器较普通模糊神经网络控制器和模糊控制器具有更优越的控制性能。     

基于神经网络的热风炉的模糊控制

针对热风炉燃烧控制的特点,将模糊控制技术与神经网络技术相结合,提出了一种基于模糊神经网络的热风炉燃烧控制方法。该方法充分考虑了系统非线性、难以建模和具有强耦合性的特点,应用模糊神经网络对模糊规则进行快速提取,通过模糊学习,解决了模糊控制应用中规则难以获取的问题。     

文化差分进化算法及其在化工过程建模中的应用

提出了一种新的文化差分进化算法,该算法将差分进化算法作为文化算法的种群空间,在文化算法的信念空间和影响函数设计中提出了基于多种知识源的设计方法,通过多种知识指导差分进化的变异操作和交叉操作,使知识的表达和指导种群进化的能力得到加强。函数测试结果表明,基于知识机制的引入使得文化差分进化算法在寻优性能上比差分进化算法有了较大的提高,而对参数的敏感性却相对较小。将文化差分进化算法用于训练补偿模糊神经网络,建立乙烯精馏塔产品质量软测量模型。通过训练与泛化能力的比较结果表明,基于文化差分进化算法的补偿模糊神经网络软测量模型在建模精度和泛化性能上均优于常规补偿模糊神经网络、模糊神经网络以及采用遗传算法优化的模型,具有更好的应用前景。     

基于模糊神经网络的位置控制器设计

针对传统HD控制方法的不足,提出了一种TSK型模糊神经网络控制器的设计方法,并用于永磁直流无刷电机伺服控制系统的位置控制.该方法中使用了一种TSI(型递归模糊神经网络,可同时动态在线进行结构学习和参数学习,以提高位置控制静态精度和动态跟踪性能,仿真结果表明,所设计的TSK型模糊神经网络位置控制器响应速度快,跟踪性能好,输出精度高,动、静态特性优于传统PID.     

基于EEMD和模糊BP神经网络的滚动轴承故障诊断

针对滚动轴承故障振动信号的非平稳特征,提出一种基于总体经验模态分解(EEMD)和模糊BP神经网络的故障诊断方法。首先对滚动轴承的振动信号采用总体经验模态分解方法进行分解,得到若干个本征模态函数分量(IMF);然后提取各分量的均方差、峭度和能量,把这些特征参数作为学习集和训练集,将学习集输入到模糊BP神经网络中进行学习;最后把训练集输入到特征参数经过学习训练后的模糊BP神经网络中进行故障类型识别,并与BP神经网络进行比较。实验结果表明:所提方法能有效地应用于滚动轴承故障诊断,而且比BP神经网络具有更高的精确度。     

储层建模新技术、新方法研究——基于模糊系统的储层建模方法

本文将以模糊规则、解模糊化方法和自学习过程为核心的模糊系统引入到储层参数的建模中,提出了模糊系统插值和随机模拟的思路和实现方法,并以著名的GSL IB软件所提供的实测数据为例进行了对比分析。研究表明利用模糊系统可以有效进行地质参数的建模,与传统的地质统计学方法(克里格和序贯高斯模拟)相比。模糊系统方法在建模精度、对条件数据分布和特征参数的恢复方面均较优。这一研究成果对储层参数建模技术的发展有着重要的意义。     

Fuzzy logic model for the prediction of cement compressive strength

A fuzzy logic prediction model for the 28-day compressive strength of cement mortar under standard curing conditions was created. Data collected from a cement plant were used in the model construction and testing. The input variables of alkali, Blaine, SO₃, and C₃S and the output variable of 28-day cement strength were fuzzified by the use of artificial neural networks (ANNs), and triangular membership functions were employed for the fuzzy subsets. The Mamdani fuzzy rules relating the input variables to the output variable were created by the ANN model and were laid out in the If-Then format. Product (prod) inference operator and the centre of gravity (COG; centroid) defuzzification methods were employed. The prediction of 50 sets of the 28-day cement strength data by the developed fuzzy model was quite satisfactory. The average percentage error levels in the fuzzy model were successfully low (2.69%). The model was compared with the ANN model for its error levels and ease of application. The results indicated that through the application of fuzzy logic algorithm, a more user friendly and more explicit model than the ANNs could be produced within successfully low error margins.     

工业报警序列的模糊关联规则挖掘方法

面向寻找工业报警序列根源,抑制报警泛滥,论文提出了一种模糊加权关联规则挖掘方法,结合模糊集合、Apriori数据挖掘算法和时间序列分析挖掘报警关联规则。基于报警数据的时间约束属性和相似度约束属性,利用相似度作为模糊加权关联规则挖掘算法的权重,提高挖掘效率和准确性。并且,相对于定量表达,模糊关联规则对于操作者来说更加容易使用。工业实例验证了方法的有效性。     

Fuzzy control of ethanol concentration for emulsan production in a fed-batch cultivation ofAcinetobacter Calcoaceticus RAG-1

A fuzzy control system was organized and applied to the control of ethanol concentration in a fed-batch cultivation process for emulsan production byAcinetobacter calcoaceticus RAG-1. The membership functions and fuzzy rules were determined by sets of data and experiences obtained from the preliminary culture experiments. The input variables, error (the difference between the set point value and the process variable) and the change of the error, were fuzzified by using the membership functions and the output variable, change of the ethanol feed rate, was inferred based on the membership functions and the given fuzzy rules. To obtain the numerical value for the output variable, the center-of-gravity method was used in the defuzzification procedure. The results showed that the ethanol concentration was well regulated around optimal level and the emulsan yield was increased compared with that of the cultivation controlled by the conventional feedback control loop.     

Application of neural networks to meltblown process control

Process modeling is essential for the control of optimization and an on-line prediction is very useful for process monitoring and quality control. Up to now, no satisfactory methods have been found to model an industrial meltblown process since it is of highly dimensional and nonlinear complexity. In this article, back-propagation neural networks (BPNNs) were investigated for modeling the meltblown process and on-line predicting the product specifications such as fiber diameter and web thickness. The feasibility of this application was successfully demonstrated by agreement of the prediction results from the BPNN to the actual measurements of a practical case. The network inputs included extruder temperature, die temperature, melt flow rate, air temperature at die, air pressure at die, and die-to-collector distance (DCD). The output of the fiber diameter was obtained by neural computing. The network training was based on 160 sets of the training samples and the trained network was tested with 70 sets of test samples which were different from the training data. This research is preliminary and of industrial significance and especially valuable for the optimal control of advanced meltblown processes. © 1996 John Wiley & Sons, Inc.     

Fuzzy modeling of signal transduction networks

This work proposes a fuzzy modeling-based approach for describing signal transduction networks. Many key steps in signal transduction mechanisms have been investigated and described qualitatively in the literature, however, only little quantitative information is available. Fuzzy models can make use of this situation as fuzzy rules can be based upon the qualitative information that is found in the literature whereas training of the model can be performed with data that is available. This combination of a fuzzy rule set based upon qualitative information with parameters to be determined from data can result in models where fewer parameters need to be estimated than if fundamental or black-box models were used. The presented fuzzy modeling procedure is used to describe two signal transduction pathways, one for IL-6 and one for TNF-α signaling. It is shown that the resulting models are capable of capturing the dynamics of key components of both signal transduction pathways.     

A novel online affine model identification of multivariable processes using adaptive neuro-fuzzy networks

This paper presents a novel systematic identification methodology for online affine modeling of multivariable processes using adaptive neuro-fuzzy networks. The proposed approach introduces an integrated procedure to simultaneously estimate a number of adaptive neuro-fuzzy networks with simple and compact dynamic structures to realize a multivariable affine model identification in real-time. A new fuzzy rule significance concept, based on a generic time-weighted rule activation record (WRAR), together with a measure of time-weighted root mean square (WRMS) error are incorporated to maintain efficient structural and parametric mechanisms for proper adaptation of the resulting neuro-fuzzy networks. An extended Kalman filter (EKF) algorithm is developed to adaptively adjust the neuro-fuzzy free parameters corresponding to the nearest created fuzzy rules. Extensive simulation test studies will be conducted to explore the capabilities of the proposed identification approach to adaptively develop online multivariable affine dynamic models for a highly nonlinear and time-varying continues stirred tank reactor (CSTR) and a highly nonlinear binary distillation column as two challenging benchmark problems.     

基于多级模糊评判与嵌套式粗糙集理论的深井巷道支护方案优选体系

对深井巷道支护方案选择体系进行了层次化分析,利用相对重要程度相关等级计算法来确定各级影响指标的权重;利用多级模糊评判理论对各备选支护方案进行了综合分析评价,针对评价结果选择最优方案.同时,以各方案的评判结果作为决策属性,以各影响因素作为条件属性,对深井巷道支护方案优选体系进行了嵌套式粗糙集理论分析,简化了系统分析的复杂性,降低了深井巷道方案优选的复杂程度,实践证明,该方法科学可行,为深井巷道支护方案优选与规律分析提供了一种新的思路