Support vector regression modeling in recursive just-in-time learning framework for adaptive soft sensing of naphtha boiling point in crude distillation unit

Prediction of primary quality variables in real time with adaptation capability for varying process conditions is a critical task in process industries.This article focuses on the development of non-linear adaptive soft sensors for prediction of naphtha initial boiling point(IBP)and end boiling point(EBP)in crude distillation unit.In this work,adaptive inferential sensors with linear and non-linear local models are reported based on recursive just in time learning(JITL)approach.The different types of local models designed are locally weighted regression(LWR),multiple linear regression(MLR),partial least squares regression(PLS)and support vector regression(SVR).In addition to model development,the effect of relevant dataset size on model prediction accuracy and model computation time is also investigated.Results show that the JITL model based on support vector regression with iterative single data algorithm optimization(ISDA)local model(JITL-SVR:ISDA)yielded best prediction accuracy in reasonable computation time.

First light on an adaptive optics system using a non-modulation pyramid wavefront sensor for a 1.8 m telescope

Our adaptive optics system based on a non-modulation pyramid wavefront sensor is integrated into a 1.8 m astronomical telescope installed at the Yunnan Observatory in LiJiang,and the first light with high-resolution imaging of an astronomical star is successfully achieved.In this Letter,the structure and performance of this system are introduced briefly,and then the observation results of star imaging are reported to show that the angular resolution of an adaptive optics system using a non-modulation pyramid wavefront sensor can approach the diffraction limit quality of a 1.8 m telescope.