In this paper, a support vector regression (SVR) using radial basis function (RBF) kernel is proposed using an integrated
parallel linear-and-nonlinear model framework for empirical modeling of nonlinear chemical process systems. Utilizing
linear orthonormal basis filters (OBF) model to represent the linear structure, the developed empirical parallel model
is tested for its performance under open-loop conditions in a nonlinear continuous stirred-tank reactor simulation case
study as well as a highly nonlinear cascaded tank benchmark system. A comparative study between SVR and the parallel
OBF-SVR models is then investigated. The results showed that the proposed parallel OBF-SVR model retained the same
modelling efficiency as that of the SVR, whilst enhancing the generalization properties to out-of-sample data.
A study to investigate the particulate emission from a boiler of a palm oil mill plant equipped with a multi-cyclones particulate arrestor was performed and reported in this paper. The particulate emission concentration was measured at the outlet of an 8000 kg steam/h capacity water-tube typed boiler of a palm oil mill plant processing 27000 kg/h of fresh fruit bunch (FFB). The particulate sample was collected iso-kinetically using the USEPA method 5 sampling train through a sampling port made at the duct of the exiting flue gas between the boiler and a multi-cyclones unit. The results showed that the particulate emission rates exiting the boiler varied from 8.51 g/s to 126 g/s with an average of 44.3±31.6 g/s. In terms of concentration, the average particulate emission concentration exiting the boiler was 7.75±4.71 g/Nm3 (corrected to 7% oxygen concentration), ranging from 1.50 to 17.7 g/Nm3 (@7% O2) of the flue gas during the measurement. Based on the 27000 kg/h FFB processed, 6000 kg/h fiber and shell (F&S) burned and the capacity of the boiler of 8000 kg steam/h, the calculated particulate emission factor was 5.91±4.21 g particulate/kg FFB processed, 26.6±18.9 g particulate/kg F&S burned and 19.9±14.2 g particulate/kg boiler capacity, respectively. Based on the finding, in order to comply with the emission limits of 0.4 g/Nm3, the required collection efficiency of any given particulate pollution control system to consider for the mill will be between 73 and 98%, which is not easily achievable with the existing multi-cyclones unit.