Stacking approaches for the design of a soft sensor for a Sulfur Recovery Unit

In the paper a soft sensor designed to estimate the acid gases hydrogen sulfide (H2S) in the tail stream of a sulphur recovery unit (SRU) in a refinery located in Sicily, Italy, is described. In particular a model stacking approach is proposed to improve the estimation performance of the soft sensor. Neural networks, principal component analysis (PCA) and partial least squares (PLS) approaches are used for the realization of the first level's models and Simple average, neural networks and PLS are used as combination approaches. The validity of the proposed aggregation strategies has been verified by a comparison with the performance of a neural model. The obtained soft sensor will be implemented in the refinery in order to replace the measurement device during maintenance and guarantee continuity in the monitoring and control of the plant

[1]  Stephen A. Billings,et al.  Non-linear system identification using neural networks , 1990 .

[2]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[3]  Jie Zhang,et al.  Improving long range prediction for nonlinear process modelling through combining multiple neural networks , 2002, Proceedings of the International Conference on Control Applications.

[4]  Jie Zhang,et al.  Developing robust non-linear models through bootstrap aggregated neural networks , 1999, Neurocomputing.

[5]  C. Kiparissides,et al.  Inferential Estimation of Polymer Quality Using Stacked Neural Networks , 1997 .

[6]  Thomas E. Marlin,et al.  Multivariate statistical monitoring of process operating performance , 1991 .

[7]  Luigi Fortuna,et al.  SOFT ANALYSERS FOR A SULFUR RECOVERY UNIT , 2002 .

[8]  Yu-Hong Zhao.  A soft sensor based on nonlinear principal component analysis , 2003, Proceedings of the 2003 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.03EX693).

[9]  Luigi Fortuna,et al.  Neural Networks for Benzene Percentage Monitoring in Distillation Columns , 1999, IIA/SOCO.

[10]  Jie Zhang.  Improved on-line process fault diagnosis using stacked neural networks , 2002, Proceedings of the International Conference on Control Applications.

[11]  S. A. Billings,et al.  Non-Linear Systems Identification Using Neural Networks , 1989 .

[12]  Luigi Fortuna,et al.  Cross correlation analysis of residuals for the selection of the structure of virtual sensors in a refinery , 2005, 2005 IEEE Conference on Emerging Technologies and Factory Automation.

[13]  山川 烈,et al.  Soft Computing , 2000, Soft Comput..

[14]  Sherif Hashem,et al.  Optimal Linear Combinations of Neural Networks , 1997, Neural Networks.

[15]  Rubens Maciel Filho,et al.  Soft sensors development for on-line bioreactor state estimation , 2000 .

[16]  J. Macgregor,et al.  Development of inferential process models using PLS , 1994 .

[17]  L. T. Fan,et al.  Monitoring the process of curing of epoxy/graphite fiber composites with a recurrent neural network as a soft sensor , 1998 .

[18]  B. Kowalski,et al.  Partial least-squares regression: a tutorial , 1986 .

[19]  Chonghun Han,et al.  A nonlinear soft sensor based on multivariate smoothing procedure for quality estimation in distillation columns , 2000 .

[20]  David H. Wolpert,et al.  Stacked generalization , 1992, Neural Networks.

[21]  Gary Montague,et al.  Soft-sensors for process estimation and inferential control , 1991 .

[22]  Jie Zhang,et al.  A comparison of different methods for combining multiple neural networks models , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[23]  Eric B. Bartlett,et al.  An information theoretic approach for combining neural network process models , 1999, Neural Networks.