A dual approach for modelling and optimisation of industrial urea reactor: Smart technique and grey box model

“…There are a number of reported studies ( [2]; [3]; [4]; [5]; [6]; [7]; [8]; [9]; [10]; [11] and [12]) on mathematical modeling and/or simulation synthesis section -the reaction section. Nevertheless, there is still a range of restrictions for simulating such a complex process.…”

Section: Introductionmentioning

confidence: 99%

“…Deviations from industrial data were reported as less than 5.0% for liquid composition in the reactor outlet. Zendehboudi et al (2014) proposed a mathematical model for urea reactor based in a UNIQUAC approach. When compared to industrial data, deviation less than 2.3% for the liquid outlet stream is obtained.…”

Section: Introductionmentioning

confidence: 99%

Industrial Urea Process – Simulation and Validation

Chinda¹,

Yamamoto²,

Lima³

et al. 2019

IJAERS

View full text Add to dashboard Cite

Due to a variety of applications, there is an ever-increasing demand for urea and subsequently its production process remains a popular research topic. In the current climate however, studies for solving industrial challenges and the search for a more sustainable process design are required. Previous works concerning simulation of industrial scale production have been developed, however almost none of them are reproducible nor consider urea quality parameters. The severe process operating conditions and the lack of biuret information are the main challenges in modeling and simulating such complex process. This paper proposes a systematic approach for simulation and validation of the current urea production process. Industrial data from the largest operational urea facility in Latin America are used. Simulation is validated against more than 30 industrial parameters. Deviation of less than 6% is obtained for mass composition and less tha n 8% for other variables considered. This work is a key point for retrofit studies and design of new processes models.

show abstract

“…ANN fits any complex nonlinear functions, given sufficient complexity of the trained network . ANN has been applied successfully to many areas in chemical engineering, such as cracking furnace modelling and optimization, optimization of CO 2 capture cost using ANN surrogate models, optimization of industrial urea reactors, frictional pressure drop of tapered bubble columns, and estimation of gas‐oil minimum miscibility pressure using PSO‐ANN …”

Section: Introductionmentioning

confidence: 99%

“…ANN fits any complex nonlinear functions, given sufficient complexity of the trained network. [15] ANN has been applied successfully to many areas in chemical engineering, such as cracking furnace modelling and optimization, [16][17][18][19] optimization of CO 2 capture cost using ANN surrogate models, [20,21] optimization of industrial urea reactors, [22] frictional pressure drop of tapered bubble columns, [23] and estimation of gas-oil minimum miscibility pressure using PSO-ANN. [24] Although ANN has powerful function approximation ability, clear mathematical expression, and easy availability of implementation for training and analysis, the success of its application usually depends on structure selection and distribution of training data.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Sampling for Surrogate Modelling with Artificial Neural Network and its Application in an Industrial Cracking Furnace

Jin

et al. 2016

Can J Chem Eng

View full text Add to dashboard Cite

In surrogate modelling, a simple functional approximation of a complex system model is always constructed to reduce the computational expense, and the selection of a suitable surrogate model and a sampling method are key to obtaining a surrogate model for a complex system. To construct an appropriate surrogate model, three methods of adaptive surrogate modelling that use artificial neural networks (ANN) are developed by incorporating a new mechanism for automatically determining the number of hidden nodes and/or a new prediction error-based mixed adaptive sampling method. In the automatic determination, the number of hidden nodes can adaptively change according to the effective rate of parameters in the ANN during the adaptive surrogate modelling process. As a result, an improper number of hidden nodes determined by the empirical method can be avoided. The prediction error-based mixed adaptive sampling method is capable of finding the strong nonlinear behaviour of the underlying system, which is easily missed by the traditional prediction variance-based sampling method. The three methods and the previous method for adaptive surrogate modelling that use ANN are tested and compared in terms of replicating the behaviours of three types of challenge functions to determine the efficacy of the developed methods. Furthermore, these methods are used in an engineering problem of surrogate modelling for a cracking reaction simulator to validate the efficacy of the developed methods.

show abstract

A dual approach for modelling and optimisation of industrial urea reactor: Smart technique and grey box model

Cited by 26 publications

References 27 publications

Utilization of support vector machine to calculate gas compressibility factor

Utilization of support vector machine to calculate gas compressibility factor

Industrial Urea Process – Simulation and Validation

Adaptive Sampling for Surrogate Modelling with Artificial Neural Network and its Application in an Industrial Cracking Furnace

Contact Info

Product

Resources

About