Presentations

These are presentations made at conferences, universities and companies. A small info bullet is posted and a PDF file of the related slides is attached.

Mass & energy balance-assisted data-driven models.

In a 2022 publication in Computers and Chemical Engineering (see here), we used material and energy balances and the time-resolved temperature measurements to back-calculate the values of reaction rates assisted at different times during a set of batch polymerization runs. These back-calculated data of the reaction rates are used to estimate DRSM models. We can then optimize the batch process without the need for an explicit model of the polymerization rate. 

DRSM Models for Nonlinear MPC

In a 2021 paper presented at the 7th IFAC Conference on nonlinear MPC, we demonstrated how to use DRSM models to design nonlinear MPC controllers. This was an effort in collaboration with Prof. Pannocchia at the University of Pisa, Italy. 

A great honor for one of our Ph.D. graduates

In the September issue of the CEP journal, the AIChE announced the selection of the winners of its 35 Under 35 Award winners.  This award honors engineers under the age of 35 who have made significant contributions to the Institute and to the chemical engineering profession.  AIChE and the Young Professionals Committee (YPC), with support from the AIChE Foundation, are recognizing this year’s 35 outstanding young AIChE members.

The AIChE 35 Under 35 Award was founded to recognize young chemical engineers who have achieved greatness in their fields. The winners are a group of driven, engaged, and socially active professionals, representing the breadth and diversity that chemical engineering exemplifies.

This year, one of the 35 awardees is Dr. Zhenyu Wang, a graduate of the Chemical and Biological Engineering Department at Tufts and a member of the SRI group.  At Dow’s Chemometrics and Artificial Intelligence Group, Wang develops data analytics methodologies to support Manufacturing 4.0 initiatives.  He has developed and implemented techniques to solve complex industrial problems in the areas of process monitoring, fault diagnosis, industrial process optimization, and supply chain optimization.  His goal is to make the chemical industry more efficient and sustainable. See the complete article here.

Industrial DoDE Publication

A new publication details how the DoDe methodology can be used to optimize the operation of a batch polymerization process through the development of data-driven models. The publication at the Ind. & Eng. Chem. Res. journal can be found here. 

New DRSM Publication

A new publication related to the Dynamic Response Surface Methodology (DRSM) has just been accepted.  It introduces a new time sampling strategy for the estimation of accurate DRSM models.

This strategy leads to a model with substantially reduced uncertainty and reduced correlation of parameters compared to the classical strategy of collecting samples at an equidistant interval of time. In the case study, a model of the same accuracy can be achieved with almost half of the measurements if the new sampling strategy is followed. Instead of sampling equidistantly in time, the new strategy has samples collected equidistantly in θ, an exponential transformation of time using the slowest dynamics of the process. This publication can be found here.