Adaptive prediction model for fluidized catalytic cracking processes based on the PLS method

摘要

Based on the partial least squares (PLS) method, an adaptive predictive PLS (AP-PLS) method was developed for sensitive adaptation to process changes using large-scale data (Big Data) from chemical processes. Utilizing data sets of fluidized catalytic cracking (FCC) and residue FCC (RFCC) processes as the basis, the AP-PLS method was developed and its prediction ability was compared with the simple PLS method. The required parameters for the prediction model of the FCC and RFCC processes are readily available from reported process data using time-varying model updating by the AP-PLS method. The prediction results were compared with the simple PLS method in terms of average deviations from the real process data. This approach can be used for reasonably accurate prediction of product variables and can adapt to process changes in large-scale chemical processes such as FCC and RFCC.