First-Principles, Data-Based, and Hybrid Modeling and Optimization of an Industrial Hydrocracking Unit

Abstract

The first-principles, data-based, and hybrid modeling strategies are employed to simulate an industrial hydrocracking unit, to make a comparative performance assessment of these strategies, and to do optimization. A first-principles model (FPM) based on the pseudocomponent approach (Bhutani, N.; Ray, A. K.; Rangaiah, G. P. Ind. Eng. Chem. Res. 2006, 45, 1354 is coupled with neural network(s) in different hybrid architectures. Data-based and hybrid models are promising for important predictions in the presence of variations in operating conditions, feed quality, and catalyst deactivation. Data-based models are purely empirical and are developed using neural networks, whereas the neural-network component of a hybrid model is used to obtain either updated model parameters in the FPM connected in series or to correct predictions of the FPM. This article presents data-based models and three hybrid models, their implementation and evaluation on an industrial hydrocracking unit for predicting steady-state performance, and finally the optimization of the hydrocracking unit using the data-based model and a genetic algorithm.

5-Lumps kinetic modeling, simulation and optimization for hydrotreating of atmospheric crude oil residue

“…The hydrotreating of RCR using trickle bed reactor was tested under various LHSV (0.3-1 h -1 ), temperature (653-693 K), and pressure (6,8,10 MPas) over (Ni-Mo/c- Al 2 O 3 ) to determine the reaction kinetics by analyzing the results obtained depending on experiments and using kinetic models within gPROMS program. The increase in process yield happened due to the kinetic parameters used to describe hydrotreating processes in this model that are affected by the operating conditions.…”

“…However, the available analytical techniques are incapable to identify the detailed molecular level of heavy feedstocks [9]. There are other types of modeling used to determine reactor performance such as hybrid modeling which is a first-principles model (FPM) based on the pseudo-component approach coupled with neural network(s) in different hybrid architectures [10], Combination of Genetic Algorithm and Sequential Quadratic Programming which based on genetic algorithm and sequential quadratic programming to determine the significant reactions and their corresponding rate constants [11], and some used kinetics to extract information about yield [12] and other model of hydrocracking reactor [13]. The lumped kinetic models are commonly used in modeling the hydrocracking of heavy feedstocks such as atmospheric vacuum resides.…”

Optimizing an Industrial Scale Naphtha Catalytic Reforming Plant Using a Hybrid Artificial Neural Network and Genetic Algorithm Technique

“…ANNs can be also applied as hybrid models. The term hybrid modeling is used to describe the incorporation of prior knowledge about the process under consideration in a neural network modeling approach [9,10].…”

Modeling and Optimizing a Vacuum Gas Oil Hydrocracking Plant using an Artificial Neural Network

“…This technique is based on information compiled from the process, and without any need for identifying the physical and chemical characteristics of the feed and products, the desired outputs, such as yield or conversion, can be simulated . In this respect, many researchers have modeled or optimized the VGO hydrocracking process; however, most of them reported increases in the yield of specific products (middle distillate or naphtha), regardless of the profit, process limitations, and catalyst life (Bhutani et al, 2006;Bahmani et al, 2010;Alhajree et al, 2011;Vasseghian & Ahmadi, 2014). Moreover, this method was applicable for simulating the behavior of intricate relationship processes, such as the catalytic-dielectric barrier discharge plasma system (Istadi & Amin, 2006;Istadi & Amin, 2007).…”