东南大学学报（英文版）2004，Vol.20Issue(1)：65-69,5.
非线性偏最小二乘法在催化剂建模中的应用
Application of nonlinear partial least square in catalyst modeling
黄凯 1罗正鸿 2陈丰秋 3吕德伟2
作者信息
- 1. 东南大学化学化工系,南京,210096
- 2. 浙江大学化学工程系,杭州,310027
- 3. 厦门大学化学工程系,厦门,361005
- 折叠
摘要
Abstract
In this paper neural network partial least square (NNPLS) was used to establish a robust reaction model for a multi-component catalyst of methane oxidative coupling. The details, including the learning algorithm, the number of hidden units of the inner network, activation function, initialization of the network weights and the principal components, are discussed. The results show that the structural organizations of inner neural network are 1-10-5-1, 1-8-4-1, 1-8-5-1, 1-7-4-1, 1-8-4-1, 1-8-6-1, respectively. The Levenberg-Marquardt method was used in the learning algorithm, and the central sigmoidal function is the activation function. Calculation results show that four principal components are convenient in the use of the multi-component catalyst modeling of methane oxidative coupling. Therefore a robust reaction model expressed by NNPLS succeeds in correlating the relations between elements in catalyst and catalytic reaction results. Compared with the direct network modeling, NNPLS model can be adjusted by experimental data conveniently and the calculation of the model is simpler and faster than that of the direct network model.关键词
偏最小二乘法/催化剂/甲烷氧化偶联/神经网络/建模Key words
partial least square/catalyst/oxidative coupling of methane/neural network/modeling分类
化学化工引用本文复制引用
黄凯,罗正鸿,陈丰秋,吕德伟..非线性偏最小二乘法在催化剂建模中的应用[J].东南大学学报（英文版）,2004,20(1):65-69,5.
