基于NNPLS的丁苯橡胶门尼粘度预测  

Prediction for the Mooney-Viscosity of SBR Based on NNPLS

作　　者：李桢[1] 肖迳[2] 刘美[3] 

机构地区：[1]中国石化股份有限公司茂名分公司,广东茂名525000 [2]华南理工大学自动化科学与工程学院,广东广州510640 [3]茂名学院自动化系,广东茂名525000

出　　处：《微计算机信息》2008年第30期247-249,共3页Control & Automation

基　　金：国家自然科学基金"基于统计学习的复杂系统建模及控制技术研究"(60704012);广东省自然科学基金"连续搅拌反应釜的先进控制技术研究"(06300232);广东省科技计划项目(2004B10301035);茂名市科技计划项目(201095)

摘　　要：门尼粘度是合成橡胶生产的主要质量指标,如何在线监测门尼粘度,并实现质量的自动监控是橡胶生产工业亟待解决的问题。本文应用NNPLS方法建立生产过程门尼粘度预测模型。结合工艺机理分析,找出影响橡胶门尼粘度的主要参数,确定辅助变量,建立基于NNPLS的门尼粘度预测模型。仿真结果,门尼粘度预测值与实际值最大误差为3.6,预测模型精度高,泛化能力强,运行速度快,可以指导生产。Mooney-viscosity is the main quality index of Synthetic Rubber. Monitoring the Mooney-viscosity effectively and realizing automatic quality control of production process is an urgent problem in the rubber industry. This paper proposes a prediction model of the Mooney-viscosity based on NNPLS. Several major parameters affecting the Mooney-viscosity were chosen based on mechanism analysis and used as secondary variables. Then a prediction model for the Mooney-viscosity was established by NNPLS. The simulation results show that the maximum error of Mooney-viscosity was 3.6. The model features high accuracy, good approximation and generalization ability. This data may be used to efficiently guide production.

关 键 词：丁苯橡胶 门尼粘度 预测 神经网络部分最小二乘 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]