Autoregressive neural network for model predictive control of multivariable cracking catalyst calcinator

Guzairov, Murat; Gabitov, R. F.; Kayashev, A. I.; Muravyova, E. A.

doi:10.3103/s1060992x11030027

Cited by 5 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With an uncontrolled drive, the question of carefully selecting the diameters of actuators' throttling devices arises, which is a very complex and expensive task [16][17][18]. It is necessary to select the shape of a plunger of the throttling device.…”

Section: Operationmentioning

confidence: 99%

Development and Research of a Dynamic Flow Laboratory Bench Model

Muravyova¹,

Popkov²

2019

Proceedings of the 7th Scientific Conference on Information Technologies for Intelligent Decision Making Support (ITIDS 2019)

View full text Add to dashboard Cite

The article is devoted to the development and research of a flow laboratory bench model based on highprecision measuring instruments "KROHNE". The following instruments were used: electromagnetic flowmeter ALTOFLUX IFM 5080 K, mass meter Korimass 10G + MFM 4085 K/F, electromagnetic flow rate meter DWM 2000. Highly intelligent instruments allow more accurate selection of the necessary amount of raw materials and other initial components, also maintain process parameters, and maintain pressure, level, and temperature at a set level. This makes it possible to increase the yield of final products, to reduce the amount of produced waste, to reduce waste disposal costs and to reduce energy costs thanks to more precise process run. The conducted studies with uncontrolled and controlled drives depending on the power consumption, which depends on the flow, have shown that it is possible to obtain power savings from 34% to 75%.

show abstract

Section: Operationmentioning

confidence: 99%

Development and Research of a Dynamic Flow Laboratory Bench Model

Muravyova¹,

Popkov²

2019

Proceedings of the 7th Scientific Conference on Information Technologies for Intelligent Decision Making Support (ITIDS 2019)

View full text Add to dashboard Cite

show abstract

“…A nonlinear NN-based MPC controller, for use in processes with an integrating response exhibiting long dead time, is designed and successfully applied to the temperature control of a semi-batch reactor in [ 9 ]. The calcination process within the production of high-octane engine fuels is shown to be successfully under control of a NN-based MPC integrated system, and capable of significantly lowering plant costs in [ 10 ]. Further progress on neural-based MPC is catalyzed by recent developments in: (a) NN training algorithms, which help to increase the predictive model accuracy and consequently the controller performance [ 11 ]; and (b) nonlinear search methods, which enable the incorporation of multi-objective, large-scale optimization problems in MPC [ 12 , 13 ].…”

Section: Introductionmentioning

confidence: 99%

An Inverse Neural Controller Based on the Applicability Domain of RBF Network Models

Alexandridis

Stogiannos

Papaioannou

et al. 2018

Sensors

View full text Add to dashboard Cite

This paper presents a novel methodology of generic nature for controlling nonlinear systems, using inverse radial basis function neural network models, which may combine diverse data originating from various sources. The algorithm starts by applying the particle swarm optimization-based non-symmetric variant of the fuzzy means (PSO-NSFM) algorithm so that an approximation of the inverse system dynamics is obtained. PSO-NSFM offers models of high accuracy combined with small network structures. Next, the applicability domain concept is suitably tailored and embedded into the proposed control structure in order to ensure that extrapolation is avoided in the controller predictions. Finally, an error correction term, estimating the error produced by the unmodeled dynamics and/or unmeasured external disturbances, is included to the control scheme to increase robustness. The resulting controller guarantees bounded input-bounded state (BIBS) stability for the closed loop system when the open loop system is BIBS stable. The proposed methodology is evaluated on two different control problems, namely, the control of an experimental armature-controlled direct current (DC) motor and the stabilization of a highly nonlinear simulated inverted pendulum. For each one of these problems, appropriate case studies are tested, in which a conventional neural controller employing inverse models and a PID controller are also applied. The results reveal the ability of the proposed control scheme to handle and manipulate diverse data through a data fusion approach and illustrate the superiority of the method in terms of faster and less oscillatory responses.

show abstract

Development of a Method for Controlling the Production Process in Oil and Gas Fields Using Neural Networks

Sharipov

2021

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Autoregressive neural network for model predictive control of multivariable cracking catalyst calcinator

Cited by 5 publications

References 4 publications

Development and Research of a Dynamic Flow Laboratory Bench Model

Development and Research of a Dynamic Flow Laboratory Bench Model

An Inverse Neural Controller Based on the Applicability Domain of RBF Network Models

Development of a Method for Controlling the Production Process in Oil and Gas Fields Using Neural Networks

Contact Info

Product

Resources

About