Identification and predictive control of a FCC unit using a MIMO neural model

Vieira, W. G.; Santos, Vera; Carvalho, Florival Rodrigues de; Pereira, João Alexandre Ferreira da Rocha; Fileti, Ana Maria Frattini

doi:10.1016/j.cep.2004.08.008

Cited by 28 publications

(14 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Artificial neural network (ANN) models have been recommended for approximation of highly nonlinear complex functions. Neural networks also have been applied very successfully in the identification and control of dynamic systems (Meleiro et al, 2009;Vieira et al, 2005;Yu and Gomm, 2003). An ANN is a mathematical expression of the neural aspect of the human brain.…”

Section: Neural Netwrok Model Predictive Control (Nnmpc)mentioning

confidence: 99%

Using Neural Network Predictive Control for Riser-Slugging Suppression

Eslamloueyan¹,

Hosseinzadeh²

2009

Chemical Product and Process Modeling

View full text Add to dashboard Cite

Riser-slugging is a flow regime that can occur in multiphase pipeline-riser systems, and is characterized by severe flow and pressure oscillations. Reducing undesired slugging effects can have great economic benefits. Recently, control methods have been proposed to conquer slugging flow problems in pipeline risers. The advantages of using a control system are that it can be installed on existing oil and gas production facilities with no need for expensive equipment and no significant pressure drop is imposed to the system.In this work, a predictive control system based on Neural Network (NN) model of process is developed for handling and suppressing riser-slugging. An ANN model of the plant is used to predict future response of the nonlinear process. Storkaas dynamic model (Storkaas and Skogestad,2002) is employed for the process simulation. Comparing the results of this research to that of others, indicates that the proposed neural model predictive controller makes a significant improvement in the setpoint tracking especially for higher step change in the setpoint value.

show abstract

Section: Neural Netwrok Model Predictive Control (Nnmpc)mentioning

confidence: 99%

Using Neural Network Predictive Control for Riser-Slugging Suppression

Eslamloueyan¹,

Hosseinzadeh²

2009

Chemical Product and Process Modeling

View full text Add to dashboard Cite

show abstract

“…[1,7,8] These statistical models may be developed by means of artificial neural networks (ANNs), based on reliable process data.…”

Section: Introductionmentioning

confidence: 99%

FCCU simulation based on first principle and artificial neural network models

Miheţ

Cristea

Agachi

2009

Asia-Pacific J Chem Eng

View full text Add to dashboard Cite

A first principle model has been developed for the reactor-regenerator system based on construction and operating data from an industrial fluid catalytic cracking unit (FCCU). The first principle model takes into account the main FCCU subsystems: reactor riser, regenerator, stripper, catalyst circulation lines, air blower, wet gas compressor and main fractionator. A five-lump kinetic scheme has been considered for the reactions taking place in the reactor riser. Subsequently, an artificial neural network (ANN) model has been built for the complex FCCU system. The dynamic simulator, based on the previously developed first principle model, served as the source of reliable data for ANN design, training and testing. The ANN developed model was successfully trained and tested. Comparison between first principle and neural network based model leads to a very good match between the two models. Results show the substantial reduction of the computation time featured by the ANN model compared to the first principle model, demonstrating its potential use for real-time implementation in model-based control algorithms.  2009 Curtin

show abstract

“…Between the input and output layers, there is a variable number of hidden (hidden or intermediate) layers. For this arrangement of layers, the number of neurons in each layer and the type of connection between neurons (feedforward or feedback) defines the architecture of the neural network (Haykin, 1999;Vieira et al, 2005;Marini, 2009;Khataee and Kasiri, 2010).…”

Section: Neural Network Structure and Learningmentioning

confidence: 99%

Neural networks to formulate special fats

et al. 2012

View full text Add to dashboard Cite

RESUMEN Utilización de redes neuronales para formular grasas técnicas.Las redes neuronales son una rama de la inteligencia artificial basadas en la estructura y funcionamiento de sistemas biológicos, teniendo como principal característica la capacidad de aprender y generalizar conocimiento. Estas son utilizadas en la resolución de problemas complejos, en los cuales los sistemas computacionales tradicionales presentan una eficiencia baja. Hasta la fecha, han sido propuestas aplicaciones para los más diversos sectores y actividades. En el área de grasas y aceites, la utilización de redes neuronales se ha concentrado principalmente en dos asuntos: la detección de adulteraciones y la formulación de productos grasos. La formulación de grasas para uso específico es el caso clásico de problema complejo donde un experto o grupo de expertos definen las proporciones de cada base, que al ser mezcladas proporcionaran características especificadas para el producto deseado. Algunos sistemas computacionales convencionales están disponibles actualmente para auxiliar a los expertos, sin embargo, estos sistemas presentan algunas deficiencias. En este artículo será descrito con detalles, un sistema para la formulación de productos grasos por redes neuronales (MIX) a partir de 3 o más componentes. Todas las etapas del desarrollo, incluyendo el diseño, construcción, entrenamiento, evaluación y operación de la red serán mostradas. PALABRAS CLAVE: Blending -Formulación -Grasas hidrogenadas -Grasas interesterificadas -Grasas técnicas -Redes neuronales. SUMMARY Neural networks to formulate special fats.Neural networks are a branch of artificial intelligence based on the structure and development of biological systems, having as its main characteristic the ability to learn and generalize knowledge. They are used for solving complex problems for which traditional computing systems have a low efficiency. To date, applications have been proposed for different sectors and activities. In the area of fats and oils, the use of neural networks has focused mainly on two issues: the detection of adulteration and the development of fatty products. The formulation of fats for specific uses is the classic case of a complex problem where an expert or group of experts defines the proportions of each base, which, when mixed, provide the specifications for the desired product. Some conventional computer systems are currently available to assist the experts; however, these systems have some shortcomings. This article describes in detail a system for formulating fatty products, shortenings or special fats, from three or more components by using neural networks (MIX). All stages of development, including design, construction, training, evaluation, and operation of the network will be outlined.

show abstract

Identification and predictive control of a FCC unit using a MIMO neural model

Cited by 28 publications

References 8 publications

Using Neural Network Predictive Control for Riser-Slugging Suppression

Using Neural Network Predictive Control for Riser-Slugging Suppression

FCCU simulation based on first principle and artificial neural network models

Neural networks to formulate special fats

Contact Info

Product

Resources

About