arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.13822eess.SYcs.LGcs.SY
收藏

基于半监督学习的生化过程数据驱动软测量

Semi-supervised Learning for Data-driven Soft-sensing of Biological and Chemical Processes

Technische Universität Berlin(柏林工业大学)

Erik Esche, Torben Talis, Joris Weigert, Gerardo Brand-Rihm, Byungjun You, Christian Hoffmann, Jens-Uwe Repke

摘要:

连续操作的(生物)化学过程越来越多地遭受外部干扰,例如进料波动或市场条件的变化。产品质量通常取决于对很少测量的浓度的控制,这些浓度的测量是昂贵的。半监督回归是机器学习的一种可能的构建块和方法,用于为这种不经常测量的状态构建软传感器。使用两个案例研究,即,Williams-Otto过程和生物乙醇生产过程,将半监督回归与标准回归进行比较,以评估其优点及其在(生物)化工过程控制中的可能应用范围。

英文摘要:

Continuously operated (bio-)chemical processes increasingly suffer from external disturbances, such as feed fluctuations or changes in market conditions. Product quality often hinges on control of rarely measured concentrations, which are expensive to measure. Semi-supervised regression is a possible building block and method from machine learning to construct soft-sensors for such infrequently measured states. Using two case studies, i.e., the Williams-Otto process and a bioethanol production process, semi-supervised regression is compared against standard regression to evaluate its merits and its possible scope of application for process control in the (bio-)chemical industry.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑