光谱油样分析监测技术中的神经网络预测方法

光谱油样分析是机械磨损状态监测与故障诊断的重要技术,基于光谱数据的机械状态预测有利于发现机械系统的早期磨损故障。由于神经网络对于非线性模型的辨识和非平稳信号的预测,与传统预测模型相比具有明显的优势,文章将神经网络预测方法运用于光谱分析,提出了基于神经网络预测的光谱分析监测技术。在预测模型中采用了三层BP网络模型,针对神经网络的结构对于信号预测或模型辨识的精度具有影响很大的问题,文章利用遗传算法,对神经网络输入节点数、隐层节点数和网络收敛的均方误差(MSE)目标值进行了优化,得到了最优的网络预测模型。最后,对某发动机实际的光谱分析数据进行了预测和分析,并与传统ARMA模型的预测结果进行了比较,结果充分表明了本方法的有效性和优越性。     

人工神经网络—近红外光谱法用于甲氧苄胺嘧啶粉末药品的非？…

近红外(NIR)光谱分析技术已应用于制药、化妆品、烟草、食品、化学药品、聚合物、纺织品、油漆涂料、煤炭和石油工业等各个领域的质量监控.近年来,NIR光谱分析技术也应用于药品分析中,因该方法具有非破坏性,样品不需要复杂的预处理和分离即可直接测定.它可对药物进行定性和定量测定以及多晶、光学异构体和湿度的测定.近红外光谱法用于无损非破坏测定胶囊类以及片剂的研究已有报道[1,2].NIR光谱在使用中也有一定的局限性,主要是结构复杂,谱图重叠多,在进行定性和定量分析中需采用一定的数据处理才能获得准确可靠的分析结果.在定量分析中,…     

基于BP算法的企业自我实现能力综合评价

针对企业需要的多层次及动态复杂性特征．结合企业需要层次理论。在建立企业自我实现能力指标体系的基础上。构造了基于改进的BP算法的企业自我实现能力综合测评模型。该模型具有较好的收敛速度和自适应能力。具有方便、准确、可靠、快速等特点。实证分析和仿真结果的比较表明该算法是有效的。     

The primary design of advanced ground-based atmospheric microwave sounder and retrieval of physical parameters

This paper introduces a prototype of ground-based atmospheric microwave sounder that operates in K-band from 22 to 31 GHz and V-band from 51 to 59 GHz. Different from the MP3000A and RPG, the sounder adopts independent dual-band reflectors instead of sharing a dual-band reflector. The direct detect type receiver is applied, which is of smaller size, higher sensitivity, efficient data observing and lower nonlinear error than the widely used superheterodyne receiver. The observing brightness temperatures from this prototype agree well with the simulated brightness temperatures according to the ground-based radiative transfer theory. We use the artificial neural network (ANN) algorithm to retrieve temperature profiles, which has higher spatial resolution especially in the capping inversion when compared with the linear regression algorithm. The temperature retrievals are comparable with the retrievals from RPG and MP3000A retrieval models and have a smaller bias in some certain regions.     

Modeling of Swelling Behaviors of Acrylamide-Based Polymeric Hydrogels by Intelligent System

Hydrogels based on acrylamide (AAm) were synthesized by free radical polymerization in an aqueous solution using N,N’-methylenebisacrylamide (MBAAm) as crosslinker. To obtain anionic hydrogels, 2-acrylamido-2-methylpropanesulfonic acid sodium salt (AMPS) and acrylic acid (AAc) were used as comonomers. The swelling behaviors of all hydrogel systems were modeled using an artificial neural network (ANN) and compared with a multivariable least squares regression (MLSR) model and phenomenal model. The predictions from the ANN model, which associated input parameters, including the amounts of crosslinker (MBA) and comonomer, and swelling values with time, produce results that show excellent correlation with experimental data. The parameters of swelling kinetics and water diffusion mechanisms of the hydrogels were calculated using the obtained experimental data. Model analysis indicated that the ANN models could accurately describe complex swelling behaviors of highly swellable hydrogels.     

Optimization of the numerical treatment of the Darcy–Forchheimer flow of Ree–Eyring fluid with chemical reaction by using artificial neural networks

In this study, Darcy Forchheimer flow paradigm, which is a useful paradigm in fields such as petroleum engineering where high flow velocity effects are common, has been analyzed with artificial intelligence approach. In this context, first of all, Darcy–Forchheimer flow of Ree–Eyring fluid along a permeable stretching surface with convective boundary conditions has been examined and heat and mass transfer mechanisms have been investigated by including the effect of chemical process, heat generation/absorption, and activation energy. Cattaneo–Christov heat flux model has been used to analyze heat transfer properties. Within the scope of optimizing Darcy–Forchheimer flow of Ree–Eyring fluid; three different artificial neural network models have been developed to predict Nusselt number, Sherwood number, and skin friction coefficient values. The developed artificial neural network model has been able to predict Nusselt number, Sherwood number, and skin friction coefficient values with high accuracy. The findings obtained as a result of the study showed that artificial neural networks are an ideal tool that can be used to model Darcy–Forchheimer Ree–Eyring fluid flow towards a permeable stretch layer with activation energy and a convective boundary condition.