This work develops a framework for building machine learning models and machine-learning-based predictive control schemes for batch crystallization processes. We consider a seeded fesoterodine fumarate cooling crystallization and dissolution process in a batch reactor and present the methodology and implementation of simulation, modeling, and controller design. Specifically, to address the experimental data scarcity problem, we first develop a one-dimensional population balance model based on published kinetic parameters that were obtained empirically to describe the formation of crystals via nucleation, growth, and agglomeration. Then, recurrent neural network (RNN) and autoencoder−RNN (AERNN) models are developed using data from extensive open-loop simulations of the semi-empirical population balance model under various operating conditions to capture the process dynamic behavior. Two model predictive control (MPC) schemes using the respective RNN and AERNN models are developed to optimize the crystallization process with respect to product yield, crystal size, number of fines in the final product, and energy consumption, while accounting for the constraints on manipulated inputs. Through open-and closed-loop simulations, it is demonstrated that the RNN and AERNN models capture the process dynamics well, and the RNN-and AERNN-based MPCs achieved the desired product yield and crystal size with significantly improved computational efficiency.

Polyaniline-grafted multiwalled carbon nanotubes (PANI-g-MWNTs)/epoxy composites were prepared by solution blending and mould casting. Transmission electron microscope, scanning electron microscope, differential scanning calorimetry, thermogravimetric analysis, electrical conductivity measurement, and tensile and flexural measurements were used to characterize the morphology, thermal, electrical, and mechanical properties of the composites. The results showed that MWNTs were encapsulated by conducting dodecyl benzene sulfonic acid-doped PANI forming a core (MWNTs)-shell (PANI) nanostructure. PANI coatings swelled in tetrahydrofuran and MWNTs were homogenously dispersed in epoxy matrix. With PANI-g-MWNTs introducing into epoxy resin, curing reaction was promoted and thermal stability of the composites was enhanced. Because of conducting PANI chains wrapping on the surface of MWNTs and well dispersion of MWNTs in epoxy matrix, electrical conductivity at room temperature of the composites was increased by seven orders of magnitude compared with neat epoxy. In the PANI-g-MWNTs/epoxy composites, terminal amino groups of PANI coatings reacted with epoxy matrix during curing reactions, which guaranteed interfacial adhesion between MWNTs and epoxy resin. Mechanical properties including tensile strength, Young's modulus, flexural strength, and flexural modulus of the composites were increased by 61%, 43%, 78%, and 49% compared with neat epoxy, respectively. V C 2012 Wiley Periodicals, Inc. J Appl Polym Sci 125: E334-E341, 2012

This work considers a seeded fesoterodine fumarate (FF) cooling crystallization and presents the methodology and implementation of a real‐time machine learning modeling‐based predictive controller to handle batch‐to‐batch (B2B) parametric drift. Specifically, an autoencoder recurrent neural network‐based model predictive controller (AERNN‐MPC) is developed to optimize product yield, crystal size, and energy consumption while accounting for the physical constraints on cooling jacket temperature. Deviations in the kinetic parameters are considered in the closed‐loop simulations to account for the B2B parametric drift, and two error‐triggered online update mechanisms are proposed to address issues pertaining to the availability of real‐time crystal property measurements and are incorporated into the AERNN‐MPC to improve the model prediction accuracy. Closed‐loop simulation results demonstrate that the proposed AERNN‐MPC with online update, irrespective of the accessibility to real‐time crystal property data, achieves a desired closed‐loop performance in terms of maximizing product yield and minimizing energy consumption.

No abstract

This work considers a seeded fesoterodine fumarate (FF) cooling crystallization and presents the methodology and implementation of a real-time machine learning modeling-based predictive controller to handle batch-to-batch (B2B) parametric drift. Specifically, an autoencoder recurrent neural network-based model predictive controller (AERNN-MPC) is developed to optimize product yield, crystal size, and energy consumption while accounting for the physical constraints on cooling jacket temperature. Deviations in the kinetic parameters are considered in the closed-loop simulations to account for the B2B parametric drift, and two error-triggered online update mechanisms are proposed to address issues pertaining to the availability of real-time crystal property measurements and are incorporated into the AERNN-MPC to improve the model prediction accuracy. Closed-loop simulation results demonstrate that the proposed AERNN-MPC with online update, irrespective of the accessibility to real-time crystal property data, achieves a desired closed-loop performance in terms of maximizing product yield and minimizing energy consumption.