Real-time process optimization based on grey-box neural models

Abstract

-This paper investigates the feasibility of using grey-box neural models (GNM) in Real Time Optimization (RTO). These models are based on a suitable combination of fundamental conservation laws and neural networks, being used in at least two different ways: to complement available phenomenological knowledge with empirical information, or to reduce dimensionality of complex rigorous physical models. We have observed that the benefits of using these simple adaptable models are counteracted by some difficulties associated with the solution of the optimization problem. Nonlinear Programming (NLP) algorithms failed in finding the global optimum due to the fact that neural networks can introduce multimodal objective functions. One alternative considered to solve this problem was the use of some kind of evolutionary algorithms, like Genetic Algorithms (GA). Although these algorithms produced better results in terms of finding the appropriate region, they took long periods of time to reach the global optimum. It was found that a combination of genetic and nonlinear programming algorithms can be use to fast obtain the optimum solution. The proposed approach was applied to the Williams-Otto reactor, considering three different GNM models of increasing complexity. Results demonstrated that the use of GNM models and mixed GA/NLP optimization algorithms is a promissory approach for solving dynamic RTO problems.

Fuzzy Logic in Genetic Regulatory Network Models

“…This is a nonlinear function, which provides for realism from a biological point of view. It is generally defined as a function of sigmoidal type, commonly the Hill function [3], [5]:…”

“…Thus, we find in the literature approaches that use the ramp function as part of the linear segments of the model [5]. This approximation of the regulation function is also known as a logoid function [3] calling such models as based on Piecewise Linear Differential Equations-Logoid(PLDE-Logoid) [20]. In this case, the curve takes the form shown in Figure 1.c, and the regulation function is defined as:…”

“…It is now possible, using the necessary experimental data, to use optimization tools or artificial intelligence to solve this problem [2], [25]. An approach to the ODE-based models is based on a Piecewise Linear Differential Equations (PLDEs) [3], [5], [7]. On the other hand, artificial intelligence techniques, including fuzzy logic, have been incorporated primarily to the classification and analysis of data obtained through Microarrays [8], [11], [21], [15], [23].…”

Vapor-Liquid equilibria modeling using gray-box neural networks as binary interaction parameters predictor

“…GNMs have been used for a wide gamut of applications, such as fed-batch bioreactors [3], Williams-Otto reactor [4], maximization in methanol conversions [5], wastewater systems [6], and empirical improvement of equations of state [7], among others.…”

Predictive Control of a Batch Polymerization System Using a Feedforward Neural Network With Online Adaptation by Genetic Algorithm

“…It is now well established that phenomenological models typically provide a more accurate description of the process, especially for extrapolation, and empirical models are easier to obtain and manipulate during online applications in real time, especially when obtaining experimental data is facilitated (Vieira et al, 2003;Cubillos et al, 2007;Janakiraman et al, 2013). For this reason, some applications require an optimization/adaptation of the model developed and eventually the use of hybrid structures, which take into account empirical knowledge plus phenomeno-logical knowledge, may be considered.…”