基于最佳投影识别法的聚全氟乙丙烯生产工艺优化

Process optimization of fluorinated ethylene propylene product based on the optimal projection recognition method

企业产品质量和工艺的波动数据中蕴含了生产规律性,利用数据挖掘方法总结波动数据中的统计规律,优化控制产品质量,是企业挖潜增效的有效技术方法;同时,企业产品的智能优化需要自动化建模技术.以聚全氟乙丙烯(fluorinated ethylene propylane, FEP)产品合格率(产品熔融指数分布满足用户指定范围的达标率)为生产优化目标,在收集生产装置有关工艺数据的基础上,利用最佳投影识别法自动建立了FEP产品熔融指数与其生产工艺参数间的关系,得到了FEP产品的生产工艺优化方案,并在实际生产中进行实施.结果显示,该方案显著提高了FEP产品的熔融指数合格率,以及企业的经济效益.

The process data of production can be utilized to investigate the regularity of production quality by using data mining,which is an effective method in industrial optimization.Furthermore,it is expected that the optimal model can be constructed in a fast and automatic way.In this project,the optimal projection recognition technique was proposed to construct the pattern recognition model for classifying different qualities of fluorinated ethylene propylene(FEP)concerning melt index.It was found that the qualified accuracy of production increased remarkably after the application of the optimal model available.