ARTICLE IN PRESS JID: JTICE [m5G;January 23, 2018;13:11] Journal of the Taiwan Institute of Chemical Engineers 000 (2018) 1–11 Contents lists available at ScienceDirect Journal of the Taiwan Institute of Chemical Engineers journal homepage: www.elsevier.com/locate/jtice A data-driven soft-sensor for monitoring ASTM-D86 of CDU side products using local instrumental variable (LIV) technique Bahareh Bidar, Mir Mohammad Khalilipour, Farhad Shahraki, Jafar Sadeghi ∗ Center for Process Integration and Control (CPIC), Department of Chemical Engineering, University of Sistan and Baluchestan, Zahedan 98164, Iran a r t i c l e i n f o Article history: Received 5 September 2017 Revised 2 December 2017 Accepted 7 January 2018 Available online xxx Keywords: Data-driven soft sensor Instrumental variable State dependent parameter Quality prediction ASTM-D86 temperature Crude distillation column a b s t r a c t Atmospheric crude distillation unit is the main unit operation in petroleum refining industries. The main difficulties in quality control of column are the availability of quality measurements. The design of prod- uct quality estimator will help improve quality monitoring and control performance in oil refinery indus- try by accurately predicting the side products properties, simultaneously. The objective of this paper is to design and implement state dependent parameter (SDP) based soft sensors using local instrumental variables (LIV) technique for an industrial atmospheric crude distillation unit. On the basis of tray tem- perature measurements of the column, soft sensor models for estimation of 95%ASTM-D86 of product streams have been developed. Three soft sensors are separately designed in an offline manner for each product quality with steady-state data of the column. The performance of proposed soft sensors is evalu- ated through testing data and also by online implementation in simulated control system. The prediction results, after tuning controller parameters, show excellent agreement with quality predictions from the rigorous model. Based on developed soft sensors, it is possible to estimate product properties in a con- tinuous manner with minimum delay compared to laboratory ASTM analysis and apply perfect control as well as compliance with product quality specifications. © 2018 Published by Elsevier B.V. on behalf of Taiwan Institute of Chemical Engineers. 1. Introduction Crude distillation unit (CDU) is one of the most important units in the refineries, which separates the preheated crude oil into re- spective product fractions like naphtha, kerosene and gas oil, etc. The stringent quality control requirement in a highly competitive market, makes it essential that all the necessary product proper- ties such as Reid vapor pressure (RVP) for volatile products, flash- point for light distillates, pour point for heavier fractions, etc. are monitored online and kept under control. These product properties are generally not available online and usually measured in an of- fline manner with intervals of 8–24 h, which may lead to improper control performance. Therefore, the product properties are con- ventionally controlled using the range of boiling points. There are three types of boiling point analysis, namely ASTM 1 -D86 (Engler), ASTM-D158 (Saybolt) and true boiling point (TBP). The ASTM-D86, among the methods, is the standard test method for distillation of petroleum products at atmospheric pressure [1]. However, chang- ∗ Corresponding author. E-mail addresses: b.bidar@pgs.usb.ac.ir (B. Bidar), a.khalilipour@eng.usb.ac.ir (M.M. Khalilipour), fshahraki@eng.usb.ac.ir (F. Shahraki), sadeghi@eng.usb.ac.ir (J. Sadeghi). 1 American Society for Testing Materials. ing the product properties within the same boiling interval by ex- ternal factors (e.g. feed characteristics) can result in non-uniformity of product quality. Thus, an inferential sensing-based control strat- egy is tenable, which needs less manual effort and maintenance cost [2,3]. The soft sensor is a key technology to infer the important qual- ity variables, which are difficult-to-measure online. However, the soft sensor is accurate enough; the predicted qualities can then be used as a feedback for automatic control and optimization pur- poses. However, there are still many problems with the existing estimators that require the development of new techniques. Nowa- days, data-driven soft sensors such as partial least squares (PLS) [4,5], artificial neural networks (ANN) [6,7], support vector regres- sion (SVR) [8,9] have gained much popularity in the industrial pro- cesses. In relation to the use of data-driven soft sensors for esti- mation of product properties in CDU, many studies have been done in recent decades. To handle the strongly correlated process variables in CDU, the principal component analysis (PCA) and PLS approaches have been used. Wang et al. [10] developed a PLS-based soft sensor and applied to an industrial CDU. The ASTM 90% distillation temperature (D90) of product streams and 14 pro- cess variables are considered as the quality index and predictors, respectively. Nevertheless, the PCA and PLS can only extract linear https://doi.org/10.1016/j.jtice.2018.01.009 1876-1070/© 2018 Published by Elsevier B.V. on behalf of Taiwan Institute of Chemical Engineers. Please cite this article as: B. Bidar et al., A data-driven soft-sensor for monitoring ASTM-D86 of CDU side products using local instru- mental variable (LIV) technique, Journal of the Taiwan Institute of Chemical Engineers (2018), https://doi.org/10.1016/j.jtice.2018.01.009