Volume 67, Issue 2 e17095
PROCESS SYSTEMS ENGINEERING

A novel adaptive sampling based methodology for feasible region identification of compute intensive models using artificial neural network

Nirupaplava Metta

Nirupaplava Metta

Applied Global Services, Applied Materials, Inc., Santa Clara, California, USA

Search for more papers by this author
Rohit Ramachandran

Rohit Ramachandran

Department of Chemical and Biochemical Engineering, Rutgers, The State University of New Jersey, Piscataway, New Jersey, USA

Search for more papers by this author
Marianthi Ierapetritou

Corresponding Author

Marianthi Ierapetritou

Department of Chemical and Biomolecular Engineering, University of Delaware, Newark, Delaware, USA

Correspondence

Marianthi Ierapetritou, Department of Chemical and Biomolecular Engineering, University of Delaware, 150 Academy St, Newark, DE 19716.

Email: [email protected]

Search for more papers by this author
First published: 06 October 2020
Citations: 9

Funding information: Consortium Agreement between Janssen Pharmaceutica, University of Ghent and Rutgers University; U.S. Food and Drug Administration, Grant/Award Numbers: 11695471, 1U01FD006487-01

Abstract

Identification of feasible region of operations in multivariate processes is a problem of interest in several fields. This is particularly challenging when the process model is black-box in nature and/or is computationally expensive, as analytical solutions are not available and the number of possible model evaluations is limited. An efficient methodology is required to identify samples where the model is evaluated for developing a computationally efficient surrogate model. In this work, an artificial neural network based surrogate model is proposed which is integrated with a statistical-based approach (Jack-knifing) to estimate the variance of the surrogate model prediction. This allows implementation of an adaptive sampling approach where new samples are identified close to the feasible region boundary or in regions of high prediction uncertainty. The proposed approach performs better than a previously published kriging based method for different dimensionality case studies.