Abstract
With the increasing trend of solving more complex and integrated optimization problems, there is a need for develo** process models that are sufficiently accurate as well as computationally efficient. In this work, we develop an algorithm for the data-driven construction of a type of surrogate model that can be formulated as a set of mixed-integer linear constraints, yet still provide good approximations of nonlinearities and nonconvexities. In such a surrogate model, which we refer to as Convex Region Surrogate (CRS), the feasible region is given by the union of convex regions in the form of polytopes, and for each region, the corresponding cost function can be approximated by a linear function. The general problem is as follows: given a set of data points in the parameter space and a scalar cost value associated with each data point, find a CRS model that approximates the feasible region and cost function indicated by the given data points. We present a two-phase algorithm to solve this problem and demonstrate its effectiveness with an extensive computational study as well as a real-world case study.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig1_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig2_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig3_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig4_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig5_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig6_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig7_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig8_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig9_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig10_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig11_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig12_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig13_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig14_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig15_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig16_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig17_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig18_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig19_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig20_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig21_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig22_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig23_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig24_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig25_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig26_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11081-015-9288-8/MediaObjects/11081_2015_9288_Fig27_HTML.gif)
Similar content being viewed by others
Notes
MATLAB version R2012a (7.14.0.739), The Mathworks Inc.
GAMS version 24.2.1, GAMS Development Corporation.
References
Barber CB, Dobkin DP, Huhdanpaa H (1996) The quickhull algorithm for convex hulls. ACM Trans Math Softw 22(4):469–483
Biegler LT, Lang Yd, Lin W (2014) Multi-scale optimization for process systems engineering. Comput Chem Eng 60:17–30
Chung PS, Jhon MS, Biegler LT (2011) Chapter 2—the holistic strategy in multi-scale modeling. Adv Chem Eng 48:59–118
Cozad A, Sahinidis NV, Miller DC (2014) Learning surrogate models for simulation-based optimization. AIChE J 60(6):2211–2227
Crowder H, Johnson EL, Padberg M (1983) Solving large-scale zero-one linear programming problems. Oper Res 31(5):803–834
Goyal V, Ierapetritou MG (2002) Determination of operability limits using simplicial approximation. AIChE J 48(12):2902–2909
Goyal V, Ierapetritou MG (2003) Framework for evaluating the feasibility/operability of nonconvex processes. AIChE J 49(5):1233–1240
Grossmann IE, Trespalacios F (2013) Systematic modeling of discrete-continuous optimization models through generalized disjunctive programming. AIChE J 59(9):3276–3295
Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning. Springer, New York
Ierapetritou MG (2001) New approach for quantifying process feasibility: convex and 1-D quasi-convex regions. AIChE J 47(6):1407–1417
Jain AK (2010) Data clustering: 50 years beyond K-means. Pattern Recogn Lett 31(8):651–666
Jain AK, Duin RPW, Mao J (2000) Statistical pattern recognition: a review. IEEE Trans Pattern Anal Mach Intell 22(1):4–37
Karwan MH, Keblis MF (2007) Operations planning with real time pricing of a primary input. Comput Oper Res 34(3):848–867
Kone ER, Karwan MH (2011) Combining a new data classification technique and regression analysis to predict the Cost-To-Serve new customers. Comput Ind Eng 61(1):184–197
Mitchell TM (1997) Machine learning. McGraw-Hill, New York
Mitra S, Grossmann IE, Pinto JM, Arora N (2012) Optimal production planning under time-sensitive electricity prices for continuous power-intensive processes. Comput Chem Eng 38:171–184
Queipo NV, Haftka RT, Shyy W, Goel T, Vaidyanathan R, Kevin Tucker P (2005) Surrogate-based analysis and optimization. Prog Aerosp Sci 41(1):1–28
Simpson TW, Peplinski JD, Koch PN, Allen JK (2001) Metamodels for computer-based engineering design: survey and recommendations. Eng Comput 17:129–150
Sung C, Maravelias CT (2007) An attainable region approach for production planning of multiproduct processes. AIChE J 53(5):1298–1315
Sung C, Maravelias CT (2009) A projection-based method for production planning of multiproduct facilities. AIChE J 55(10):2614–2630
Swaney RE, Grossmann IE (1985) An index for operational flexibility in chemical process design–part I: formulation and theory. AIChE J 31(4):621–630
Üney F, Türkay M (2006) A mixed-integer programming approach to multi-class data classification problem. Eur J Oper Res 173(3):910–920
Wang GG, Shan S (2007) Review of metamodeling techniques in support of engineering design optimization. J Mech Des 129(4):370
Xu G, Papageorgiou LG (2009) A mixed integer optimisation model for data classification. Comput Ind Eng 56(4):1205–1215
Zhang Q, Grossmann IE, Heuberger CF, Sundaramoorthy A, Pinto JM (2015a) Air separation with cryogenic energy storage: optimal scheduling considering electric energy and reserve markets. AIChE J 61(5):1547–1558
Zhang Q, Sundaramoorthy A, Grossmann IE, Pinto JM (2015b) A discrete-time scheduling model for continuous power-intensive process networks with various power contracts. Comput Chem Eng
Acknowledgments
The authors gratefully acknowledge the financial support from the National Science Foundation under Grant no. 1159443 and from Praxair.
Author information
Authors and Affiliations
Corresponding author
Electronic supplementary material
Below is the link to the electronic supplementary material.
Appendices
Appendix 1: Alternative formulation for CRS model
Instead of expressing the feasible region of a CRS model as the union of feasible convex regions, we can also formulate it as the difference of the convex hull and the union of infeasible convex regions. In our example, as shown in Fig. 28, the infeasible convex regions are the two empty polytopes.
A polytope can be seen as an intersection of a set of half-spaces of which each is bounded by the hyperplane containing the corresponding facet of the polytope. A point in the polytope, x, is then a solution of the set of constraints \(a_h^T x \le b_h \quad \forall h \in H\) where H is the set of half-spaces. This is commonly referred to as an H-representation of a polyhedron. By applying the H-representation to the infeasible regions, we can express a feasible point in the CRS model, x, as a solution to the following set of constraints:
where V is the set of vertices of the convex hull, \({\bar{R}}\) is the set of infeasible convex regions, \(H_r\) is the set of half-spaces associated with region r, and \({\bar{\epsilon}}\) is a small margin parameter. Equations (20a)–(20c) state that x is a point inside the convex hull, while Eqs. (20d)–(20f) enforce that x is not a point in the interior of any of the infeasible regions. The binary variable \(z_{rh}\) is 1 if the constraint \(a_{rh}^{\text{T}} \, x \le b_{rh}\) is violated. Note that this approach could also be used to consider “holes” in the feasible region.
Formulation (20) is not entirely equivalent to Eqs. (3b)–(3g) since points on facets shared by feasible and infeasible regions will not be feasible in (20). Moreover, the big-M parameter M in (20d) typically leads to weak LP relaxations which will likely make the alternative formulation less efficient if the numbers of feasible and infeasible convex regions are similar.
Appendix 2: Data for illustrative example
For the illustrative example, we have constructed the set of 100 data points shown in Table 7. Each data point consists of a 2-dimensional parameter vector a and a cost value g. The cost values are calculated from the parameter values using two different linear correlations, for which the corresponding constants and coefficients are listed in Table 8. The cost values for the first 52 points are generated from the first linear correlation, while the cost values for the remaining points are calculated by applying the second linear correlation.
Rights and permissions
About this article
Cite this article
Zhang, Q., Grossmann, I.E., Sundaramoorthy, A. et al. Data-driven construction of Convex Region Surrogate models. Optim Eng 17, 289–332 (2016). https://doi.org/10.1007/s11081-015-9288-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11081-015-9288-8