Practical Online Characterization of the Properties of Hydrocracking Bottom Oil via Near-Infrared Spectroscopy

Providing real-time information on the chemical properties of hydrocracking bottom oil (HBO) as feedstock for ethylene cracker while minimizing processing time, is important to improve optimization production. In this study, a novel approach estimating HBO samples was developed basis near-infrared (NIR) spectra. The main noise and extreme in spectral data were removed by combining discrete wavelet transform with principal component analysis Hotelling’s T2 test. Kernel partial least squares (KPLS) regression utilized account nonlinearities between NIR HBO. Compared regression, artificial neural network, KPLS model had better performance obtaining acceptable values root mean square error prediction (RMSEP) absolute relative (MARE). All RMSEP MARE density, Bureau Mines correlation index, paraffins, isoparaffins, naphthenes less than 1.0 3.0, respectively. accuracy industrial online measurement system during consecutive running periods predicting satisfactory. yield high value-added products increased 0.26 percentage points coil outlet temperature decreased 0.25 °C, which promoted economic benefits cracking process boosted reform from automation digitization intelligence.