Wiener-Neural-Network-Based Modeling and Validation of Generalized Predictive Control on a Laboratory-Scale Batch Reactor

Abstract

Batch reactors are large vessels in which chemical reactions take place. They are mostly found to be used in process control industries for processes such as reactant mixing, waste treatment of leather byproducts, and liquid extraction. Modeling and controlling of these systems are complex due to their highly nonlinear nature. The Wiener neural network (WNN) is employed in this work to predict and track the temperature profile of a batch reactor successfully. WNN is different from artificial neural networks in various aspects, mainly its structure. The brief methodology that was deployed to complete this work consisted of two parts. The first part is modeling the WNN-based batch reactor using the provided input–output data set. The input is feed given to the reactor, and the reactor temperature needs to be maintained in line with the optimal profile. The objective in this part is to train the neural network to efficiently track the nonlinear temperature profile that is provided from the data set. The second part is designing a generalized predictive controller (GPC) using the data obtained from modeling the reactor to successfully track any arbitrary temperature profile. Therefore, this work presents the experimental modeling of a batch reactor and validation of a WNN-based GPC for temperature profile tracking.

Neural Network-Based Hammerstein Model Identification of a Lab-Scale Batch Reactor

“…The chosen batch reactor is exothermic and the reaction equation of the chemical feed and output is highly nonlinear . Additionally, it is a nonsteady state process, and its nonlinear dynamics are represented in the first-principle model as presented by Shettigar et al, , Peng et al, and Yadav et al The experimental batch reactor setup is illustrated in Figure and its schematic model is given in Figure . The internal heating and cooling system of the custom batch reactor for the polymerization reaction help to maintain the desired reactor temperature.…”

“…Due to exothermic reactions, reaction constants with exponential terms, and the sort of polymerization reaction that takes place in the reactor, batch reactors are essentially considered as a highly nonlinear process. , In a batch process, the feed is only charged once and held at the same quantity until the batch process is finished. There is neither a continuous feed inflow nor a continuous feed outflow.…”

“…These include environmental changes, variations in the temperature of coolant flow rate over time, and jacket and reactor temperature variations ( T j and T r ). By examining the batch reactor’s and continuous stirred tank reactor nonlinear differential equations − as addressed by Shettigar et al , and Peng et al, which are provided under system dynamics, the aforementioned can be realized. The batch reactor issue can be split into two categories: (i) model identification and (ii) closed-loop control operation of a batch reactor with the formation of an ideal temperature trajectory.…”

Development of a Nonlinear Model Predictive Control-Based Nonlinear Three-Mode Controller for a Nonlinear System

“…Today the process industries of the world have begun the use of the optimal control strategies such as MPC and its derivatives for the control and optimization of the process performance. In ref , the authors have described the modeling of the batch polymerization reactor along with the reaction dynamics-based Wiener neural network (WNN). The authors have modeled the batch reactor using the recorded open-loop input–output data set with the help of the WNN algorithm and designed a linear generalized predictive controller (GPC) for the experimental validation. The input feed along with the initiator is charged all together at a time into the reactor to initiate the reaction, and the reactor temperature needs to be maintained in line with the optimal temperature profile.…”

“…The batch reactors are highly nonlinear and non-steady systems with the primary objective to maintain the reactor temperature with respect to the temperature profile. If the reactor temperature is not maintained with respect to optimal trajectory formed, the reactor may face thermal runaway issues, − which in-turn is due to the sudden conversion of a polymer into a monomer. Hence the optimal control of coolant flow-rate should be used as a manipulated variable with constant heater supply in this experimental study.…”