Unsupervised Feature Transfer for Batch Process Based on Geodesic Flow Kernel

Zheming Zhang, Fang Wang, Yusong Pang, Gaowei Yan

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

7 Downloads (Pure)

Abstract

The problem of misalignment of the original measurement model is caused by nonlinear, time-varying characteristic of the batch process. In this paper, a method based on geodesic flow kernel (GFK) for feature transfer is proposed. By mapping data into the manifold space, the feature transfer from source domain to target domain is implemented. Distribution adaptation of real-time data and modeling data is performed to reduce the distribution difference between them. The historical data through distribution adaptation is used to establish a regression model to predict the real-time data, by which the unsupervised batch process soft sensor modeling is realized. The application of predicting the concentration of penicillin between different batches during the fermentation of penicillin demonstrated that the prediction accuracy of the model can be improved more effectively than the traditional soft sensor method.

Original languageEnglish
Title of host publicationProceedings of the 32nd Chinese Control and Decision Conference, CCDC 2020
Place of PublicationPiscataway, NJ, USA
PublisherIEEE
Pages975-980
ISBN (Electronic)978-1-7281-5854-9
ISBN (Print)978-1-7281-5855-6
DOIs
Publication statusPublished - 2020
Event32nd Chinese Control and Decision Conference, CCDC 2020 - Hefei, China
Duration: 22 Aug 202024 Aug 2020

Conference

Conference32nd Chinese Control and Decision Conference, CCDC 2020
CountryChina
CityHefei
Period22/08/2024/08/20

Keywords

  • Batch process
  • feature transfer
  • geodesic flow kernel
  • penicillin
  • unsupervised

Fingerprint Dive into the research topics of 'Unsupervised Feature Transfer for Batch Process Based on Geodesic Flow Kernel'. Together they form a unique fingerprint.

Cite this