1. Multilevel LASSO-based NIR temperature-correction modeling for viscosity measurement of bisphenol-A.
- Author
-
Luan, Xiaoli, Liu, Jin, and Liu, Fei
- Subjects
BISPHENOL A ,MEASUREMENT of viscosity ,ALACHLOR ,TEMPERATURE effect ,TEMPERATURE measurements ,FORECASTING - Abstract
Temperature variation will affect the prediction accuracy when using the near-infrared (NIR) analytical model to measure the viscosity of bisphenol-A. In order to correct the effect of temperature on the prediction performance of NIR model, a multilevel least-absolute shrinkage and selection operator (LASSO) is proposed in this paper. The multilevel LASSO algorithm combines LASSO with the multilevel simultaneous component analysis (MLSCA) to enhance the robustness of the model under temperature changes and external disturbances. MLSCA is applied to decompose the molecular spectral data into two parts. One part denotes the property caused by temperature, the other means the changes of concentration. LASSO, a sparse regression model, is used to select the variables and perform the regularization to further enhance the robustness and interpretability of the model. Experimental results demonstrate the effectiveness of the proposed model in measuring bisphenol-A viscosity, which provides a more stable prediction result compared with the existing ones without temperature corrections. • Effect of temperature on viscosity analysis of bisphenol-A is firstly studied. • Multilevel least absolute shrinkage and selection operator is proposed to correct for temperature fluctuation and external disturbance. • The accuracy and robustness of Near-infrared analytical model has been simultaneously improved given temperature variation and external disturbance. • Multilevel simultaneous component analysis is used to split the spectral data into between-part and within-part for the purpose of eliminating temperature influence. • The quantitative relationship between within-part and concentration is built by least absolute shrinkage and selection operator, which is capable to select characteristic wavelengths at the same time. • Experimental results of viscosity measurement for bisphenol-A with temperature variation are compared with PLS-based temperature model and MLPCR model. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF