Zengliang Gao

Just-in-Time Correntropy Soft Sensor with Noisy Data for Industrial Silicon Content Prediction

Development of accurate data-driven quality prediction models for industrial blast furnaces encounters several challenges mainly because the collected data are nonlinear, non-Gaussian, and uneven distributed. A just-in-time correntropy-based local soft sensing approach is presented to predict the silicon content in this work. Without cumbersome efforts for outlier detection, a correntropy support vector regression (CSVR) modeling framework is proposed to deal with the soft sensor development and outlier detection simultaneously. Moreover, with a continuous updating database and a clustering strategy, a just-in-time CSVR (JCSVR) method is developed. Consequently, more accurate prediction and efficient implementations of JCSVR can be achieved. Better prediction performance of JCSVR is validated on the online silicon content prediction, compared with traditional soft sensors.

Online flooding prognosis in packed columns by monitoring parameter change in EGARCH model

In the chemical industry, packed columns are commonly used operating units for separation. However, the flooding phenomenon often reduces the efficiency of packed columns and interferes with the performance of the system. Due to this reason, research on the real-time prognosis of flooding becomes a necessity in practice. Pressure drop is a key factor that indicates flooding phenomenon in packed columns. In this paper, the trajectory of pressure drop in each time window is modeled with an exponential generalized autoregressive conditional heteroskedastic (EGARCH) process. The onset of flooding is then implied by the parameter change of the model. To capture the change in an efficient manner, a nonparametric charting technique is adopted for statistical process control (SPC). The feasibility and efficiency of the proposed method are illustrated by the experimental results.