Wiener-neural identification and predictive control of a more realistic plug-flow tubular reactor

Arefi, Mohammad Mehdi; Montazeri, Allahyar; Poshtan, Javad; Jahed‐Motlagh, Mohammad Reza

doi:10.1016/j.cej.2007.05.044

Cited by 40 publications

(33 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the output matrix in the hidden layer is rank-deficient, many solutions may exist for Eq. (8). QR factorization with column pivoting can deal with the problem [46][47][48], which is achieved by the linsolve function of MAT-LAB [49].…”

Section: Nonlinear Block Identification By the Rbfnn Modelmentioning

confidence: 99%

See 1 more Smart Citation

Novel Wiener models with a time-delayed nonlinear block and their identification

2016

View full text Add to dashboard Cite

Popular Wiener models are a combination of dominant linear behavior and static nonlinear characteristics. However, they are less accurate in dealing with problems with strong nonlinear time-delayed effects. Hence, a group of novel nonlinear models based on Wiener models are proposed in this study. The static nonlinear part of general Wiener models is replaced by a time-delayed nonlinear block. Thus, two novel Wiener models with a quasi-dynamic nonlinear block are constructed, called the Wiener-QDN models. The autoregressive with exogenous input (ARX) model is utilized to identify the dynamic linear block, and the radial basis function neural network is used to build the nonlinear part of Wiener and the Wiener-QDN models. Results reveal the effectiveness of these models in nonlinear system identification. The first test cases are systems governed by simple equations. The Wiener-QDN models can identify these systems with or without measurement noise. These models are further applied in unsteady aerodynamic modeling cases. Test cases of a NACA 0012 airfoil pitching in transonic flow indicate that both linearity and nonlinearity are well captured by the proposed Wiener-QDN models.

show abstract

Section: Nonlinear Block Identification By the Rbfnn Modelmentioning

confidence: 99%

“…Wiener models have a linear dynamic block followed by a static nonlinear function. They have been successfully utilized in modeling the PH neutralization process [5], distillation column [6], polymerization reactor [7], and plug-flow tubular reactor [8]. Currently, two basic approaches are utilized to identify Wiener models [9].…”

Section: Introductionmentioning

confidence: 99%

Novel Wiener models with a time-delayed nonlinear block and their identification

2016

View full text Add to dashboard Cite

show abstract

“…9 [16, 17]. 1/3 of 98% process settling time is used as the average switching time for the excitation signal [16]. The GMN signal has 11 input levels from +7% to -7% of the input nominal value.…”

Section: Effect Of Simultaneous Changes In Reflux Flowrate and Rebmentioning

confidence: 99%

Simulation studies of Methyl Tert-butyl Ether production in reactive distillation

Sudibyo

Murat

Aziz

2011

2011 IEEE International Conference on Control System, Computing and Engineering

View full text Add to dashboard Cite

Methyl Tert-butyl Ether (MTBE) is usually used as solvent, chemical reagent and antiknock additive to improve octane number of gasoline and can be efficiently produced using reactive distillation column. Maximum production of the MTBE can be achieved if the reaction can be kept at optimum operating conditions and column configuration. In practice, changing the column configuration such as tray or catalyst location always incurs high cost. Therefore, the development of the MTBE reactive distillation model can serve as an important tool in predicting and investigating the optimum production for MTBE without the need to run the actual experiment. Therefore, the development of the MTBE reactive distillation model is essential to simulate the process which can lead to high yields of MTBE production. In this work, a detailed equilibrium (EQ) model for continuous reactive distillation (RD) processes is developed using Aspen Plus™ and Matlab TM software. The simulation results achieved is compared with data available in the literature. The validated model is then further used to study the interaction of various inputs and output variables of the MTBE process which can be used for future empirical model development and control studies.

show abstract

“…1 Among them are chemical plants, 2 soft sensor systems, 3 thermodynamic engines, 4 physiological systems, 5 fuel cells, 6 power amplifier, 7 and tubular reactor, 8 just to name a few. For this reason, input-output signals that are obtained from the system are used to determine the parameters of the model.…”

Section: Introductionmentioning

confidence: 99%

“…These structures can describe a large number of nonlinear plants with desired accuracies. 1 Among them are chemical plants, 2 soft sensor systems, 3 thermodynamic engines, 4 physiological systems, 5 fuel cells, 6 power amplifier, 7 and tubular reactor, 8 just to name a few.…”

Section: Introductionmentioning

confidence: 99%

Real‐time identification of nonlinear multiple‐input–multiple‐output systems with unknown input time delay using Wiener model with Neuro‐Laguerre structure

Sadeghi¹,

Farrokhi

2018

Adaptive Control & Signal

View full text Add to dashboard Cite

In this article, a real-time block-oriented identification method for nonlinear multiple-input-multiple-output systems with input time delay is proposed. The proposed method uses the Wiener structure, which consists of a linear dynamic block (LDB) followed by a nonlinear static block (NSB). The LDB is described by the Laguerre filter lattice, whereas the NSB is characterized using the neural networks. Due to the online adaptation of the parameters, the proposed method can cope with the changes in the system parameters. Moreover, the convergence and bounded modeling error are shown using the Lyapunov direct method. Four practical case studies show the effectiveness of the proposed algorithm in the open-loop and closed-loop identification scenarios. The proposed method is compared with the recently published methods in the literature in terms of the modeling accuracy, parameter initialization, and required information from the system. How to cite this article: Sadeghi M, Farrokhi M. Real-time identification of nonlinear multiple-inputmultiple-output systems with unknown input time delay using Wiener model with Neuro-Laguerre structure. Int J Adapt Control Signal Process. 2019;33:157-174. https://doi.

show abstract

Wiener-neural identification and predictive control of a more realistic plug-flow tubular reactor

Cited by 40 publications

References 26 publications

Novel Wiener models with a time-delayed nonlinear block and their identification

Novel Wiener models with a time-delayed nonlinear block and their identification

Simulation studies of Methyl Tert-butyl Ether production in reactive distillation

Real‐time identification of nonlinear multiple‐input–multiple‐output systems with unknown input time delay using Wiener model with Neuro‐Laguerre structure

Contact Info

Product

Resources

About