Soft sensors for crude distillation unit product properties estimation and control

Neural network-based soft sensors are developed for quality estimation of kerosene, a refinery crude distillation unit side product. Based on temperature and flow measurements two soft sensors serve as the estimators for the kerosene distillation end point (95%) and freezing point. The neural networks are trained by the adaptive gradient method using cascade learning. Research results show possibilities of applying soft sensors for refinery product quality estimation and inferential control as an alternative for process analyzers and laboratory assays.