Logo image
Dynamic Data Reconciliation for Enhanced Control Performance of Systems with Data-Driven Model
會議論文集

Dynamic Data Reconciliation for Enhanced Control Performance of Systems with Data-Driven Model

A. Yang, W. Zhu, J. Li, Y. Yao 和 Y. Liu
Proceedings of 2025 IEEE 14th Data Driven Control and Learning Systems Conference, DDCLS 2025, 頁碼.1664-1668
2025
Web of Science ID: WOS:001600424700280

摘要

Chemical process Control performance assessment Dynamic data reconciliation Long short-term memory Measurement noise Bayesian networks Feedback Industrial electronics Process control Chemical process Control performance Control performance assessment Data-driven model Dynamic data reconciliation Feed back information Measurement Noise Model informations Process-models Short term memory Spurious signal noise
Effective control of chemical processes is an important prerequisite for ensuring production benefits. Traditionally, the influence of feedback measurement noise is not considered in the control performance assessment (CPA). In this work, a dynamic data reconciliation (DDR) filtering method is develop in a system with unknown process model to enhance the CPA results impaired by measurement noise. Firstly, the interference of measurement noise on CPA results is derived. Then, for the unknown process model, as a typical data-driven model, the long short-term memory network is used for process modeling to obtain model information. Finally, based on the measurement feedback information and model information, DDR uses Bayesian inference to obtain an optimal feedback information to enhance the reliability of CPA results. The control performance enhancement effect is demonstrated on the control process of a continuous stirred tank reactor process. © 2025 IEEE.

檔案與連結 (1)

url
https://www.scopus.com/inward/record.uri?eid=2-s2.0-105011825149&doi=10.1109%2fDDCLS66240.2025.11065368&partnerID=40&md5=706abed255d61c1973d6763bd450434a檢視

相關連結

指標

1 檢視次數

詳細資料

Logo image