Real-time quality monitoring in debutanizer column with regression tree and ANFIS
Subject Areas : Mathematical OptimizationKumar Siddharth 1 , Amey Pathak 2 , Ajaya Kumar Pani 3
1 - Department of Chemical Engineering, Birla Institute of Technology and Science, Pilani, 333031, India
2 - Department of Chemical Engineering, Birla Institute of Technology and Science, Pilani, 333031, India
3 - Department of Chemical Engineering, Birla Institute of Technology and Science, Pilani, 333031, India
Keywords: Debutanizer column . ANFIS . Regression tree . Soft sensor,
Abstract :
A debutanizer column is an integral part of any petroleum refinery. Online composition monitoring of debutanizer column outlet streams is highly desirable in order to maximize the production of liquefied petroleum gas. In this article, data-driven models for debutanizer column are developed for real-time composition monitoring. The dataset used has seven process variables as inputs and the output is the butane concentration in the debutanizer column bottom product. The input–output dataset is divided equally into a training (calibration) set and a validation (testing) set. The training set data were used to develop fuzzy inference, adaptive neuro fuzzy (ANFIS) and regression tree models for the debutanizer column. The accuracy of the developed models were evaluated by simulation of the models with the validation dataset. It is observed that the ANFIS model has better estimation accuracy than other models developed in this work and many data-driven models proposed so far in the literature for the debutanizer column.
Ahmed F, Nazir S, Yeo YK (2009) A recursive PLS-based soft sensor for prediction of the melt index during grade change operations in HDPE plant. Korean J Chem Eng 26(1):14–20
Aimin M, Peng L, Lingjian Y (2015) Neighborhood preserving regression embedding based data regression and its applications on soft sensor modeling. Chemometr Intell Lab Syst 147:86–94
Bidar B, Sadeghi J, Shahraki F, Khalilipour MM (2017) Data-driven soft sensor approach for online quality prediction using state dependent parameter models. Chemometr Intell Lab Syst 162:130–141
Breiman L, Friedman J, Stone CJ, Olshen RA (1984) Classification and regression trees. CRC Press, Hoboken
Chen WL, Huang CY, Huang CY (2013) Finding efficient frontier of process parameters for plastic injection molding. J Ind Eng Int 9(1):25
Fan M, Ge Z, Song Z (2014) Adaptive Gaussian mixture model-based relevant sample selection for JITL soft sensor development. Ind Eng Chem Res 53(51):19979–19986
Fortuna L, Graziani S, Xibilia MG (2005) Soft sensors for product quality monitoring in debutanizer distillation columns. Control Eng Pract 13(4):499–508
Fortuna L, Graziani S, Rizzo A, Xibilia MG (2007) Soft sensors for monitoring and control of industrial processes. Springer, Berlin
Ge Z (2014) Active learning strategy for smart soft sensor development under a small number of labeled data samples. J Process Control 24(9):1454–1461
Ge Z (2016) Supervised latent factor analysis for process data regression modeling and soft sensor application. IEEE Trans
Control Syst Technol 24(3):1004–1011
Ge Z, Song Z (2010) A comparative study of just-in-time-learning based methods for online soft sensor modeling. Chemometr Intell Lab Syst 104(2):306–317
Ge Z, Huang B, Song Z (2014) Nonlinear semisupervised principal component regression for soft sensor modeling and its mixture form. J Chemom 28(11):793–804
Gui WH, Li YG, Wang YL (2005) Soft sensor for ratio of soda to aluminate based on PCA-RBF multiple network. J Cent South Univ Technol 12(1):88–92
Jang JS (1993) ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybern 23(3):665–685
Jang JSR, Sun CT, Mizutani E (1997) Neuro-fuzzy and soft computing: a computational approach to learning and machine
intelligence. Prentice Hall, India
Kennard RW, Stone LA (1969) Computer aided design of experiments. Technometrics 11(1):137–148
Ljung L (1999) System Identification: theory for the User, 2nd edn. Englewood Cliffs, NJ, Prentice-Hall, USA
Markopoulos AP, Georgiopoulos S, Manolakos DE (2016) On the use of back propagation and radial basis function neural networks in surface roughness prediction. J Ind Eng Int 12(3):389–400
Pani AK, Mohanta HK (2014) Soft sensing of particle size in a grinding process: application of support vector regression, fuzzy inference and adaptive neuro fuzzy inference techniques for online monitoring of cement fineness. Powder Technol
264:484–497
Pani AK, Mohanta HK (2016) Online monitoring of cement clinker quality using multivariate statistics and Takagi–Sugeno fuzzyinference technique. Control Eng Pract 57:1–17
Pani AK, Amin KG, Mohanta HK (2016) Soft sensing of product quality in the debutanizer column with principal component analysis and feed-forward artificial neural network. Alex Eng J 55(2):1667–1674
Sharma GVSS, Rao RU, Rao PS (2017) A Taguchi approach on optimal process control parameters for HDPE pipe extrusion
process. J Ind Eng Int 13(2):215–228
Shi J, Liu XG (2006) Product quality prediction by a neural softsensor based on MSA and PCA. Int J Autom Comput 3(1):17–22
Shokri S, Sadeghi MT, Marvast MA, Narasimhan S (2015) Improvement of the prediction performance of a soft sensor model based on support vector regression for production of ultra-low sulfur diesel. Pet Sci 12(1):177–188
Steinwandter V, Zahel T, Sagmeister P, Herwig C (2017) Propagation of measurement accuracy to biomass soft-sensor estimation and control quality. Anal bioanal chem 409:693–706
Wang Y, Chen C, Yan X (2013) Structure and weight optimization of neural network based on CPA-MLR and its application in naphtha dry point soft sensor. Neural Comput Appl 22(1):75–82
Yao L, Ge Z (2017) Locally weighted prediction methods for latent factor analysis with supervised and semisupervised process data. IEEE Trans Autom Sci Eng 14(1):126–138
Yuan X, Ye L, Bao L, Ge Z, Song Z (2015) Nonlinear feature extraction for soft sensor modeling based on weighted probabilistic PCA. Chemometr Intell Lab Syst 147:167–175
Zakour SB, Taleb H (2017) Endpoint in plasma etch process using new modified w-multivariate charts and windowed regression. J Ind Eng Int 13(3):307–322
Zhang Shuning, Wang Fuli, He Dakuo, Chu Fei (2013) Soft sensor for cobalt oxalate synthesis process in cobalt hydrometallurgy based on hybrid model. Neural Comput Appl 23(5):1465–1472
Zheng J, Song Z, Ge Z (2016) Probabilistic learning of partial least squares regression model: theory and industrial applications. Chemometr Intell Lab Syst 158:80–90
Zhu J, Ge Z, Song Z (2015) Robust supervised probabilistic principal component analysis model for soft sensing of key process variables. Chem Eng Sci 122:573–584