Logo image
返回
Transfer learning soft sensor for product quality prediction in multi-grade processes
會議論文集

Transfer learning soft sensor for product quality prediction in multi-grade processes

C. Yang, B. Chen, Z. Wang, Y. Yao 和 Y. Liu
Proceedings of 2019 IEEE 8th Data Driven Control and Learning Systems Conference, DDCLS 2019, 頁碼.1148-1153
2019
DOI: https://doi.org/10.1109/DDCLS.2019.8908915

摘要

Extreme learning machine Multi-grade process Soft sensor Transfer learning Knowledge acquisition Machine learning Quality control Different operating conditions Extreme learning machine Operating condition Prediction accuracy Soft sensor models Soft sensors Transfer learning Transfer learning methods Forecasting
For multi-grade chemical processes, current data-driven soft sensor models built in a specific operating condition cannot be directly applied to predict product qualities of other conditions. A simple transfer learning method namely domain adaptation extreme learning machine (DAELM) is presented to construct a soft sensor model in multi-grade processes with limited labeled data. In addition, an effective strategy is developed to fast select the model parameters. By exploring and utilizing useful information from different operating conditions, the prediction accuracy can be improved. Compared with traditional soft sensors, the prediction results of two multi-grade chemical processes validate the advantages of DAELM. © 2019 IEEE.

檔案與連結 (1)

url
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85076392785&doi=10.1109%2fDDCLS.2019.8908915&partnerID=40&md5=ad0b5d8c6343c7e28f5c3fea0f1947a2檢視

相關連結

指標

1 檢視次數

詳細資料

Logo image