We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Soft-sensor Modeling of SMB Chromatographic Separation Process Based on Incremental Extreme Learning Machine.
- Authors
Qing-Da Yang; Cheng Xing; Jie-Sheng Wang; Yong-Cheng Sun; Yi-Peng ShuangGuan
- Abstract
Simulated Moving Bed (SMB) chromatography separation is an innovative technology that combines conventional fixed bed adsorption and true moving bed (TMB) chromatography separation techniques. Through analysis of the SMB chromatography isolation method, we have identified auxiliary variables for the soft-sensing model and key economic and technical indicators for the forecasting model. Our objective is to predict the component purity and yield of the elicit and residual solution in the SMB chromatographic separation process. To achieve this, we have utilized three different soft-sensing modeling methods: incremental extreme learning machine (I-ELM), inverse-free extreme learning machine (IF-ELM), and incremental regularized extreme learning machine (IR-ELM). Our simulation results demonstrate the effectiveness and accuracy of these ELM methods in predicting essential economic and technical gauges in the SMB chromatographic separation process. These methods enable instantaneous, optimized, and resilient operation of SMB chromatography separation. Overall, SMB chromatography separation represents an advanced technology that enhances traditional techniques, and our study highlights the efficacy of various ELM methods in predicting essential process indicators, thereby ensuring optimal operation.
- Subjects
MACHINE learning; TECHNOLOGICAL innovations; MOVING bed reactors; CHROMATOGRAPHIC analysis; ECONOMIC indicators
- Publication
IAENG International Journal of Computer Science, 2023, Vol 50, Issue 4, p1532
- ISSN
1819-656X
- Publication type
Article