Recurrent Neural Network based Soft Sensor for Monitoring and Controlling a Reactive Distillation Column

Abstract For the real time monitoring of a Reactive Distillation Column (RDC), a Recurrent Neural Network (RNN) based soft sensor has been proposed to estimate the bottoms product composition of the RDC for the synthesis of n-Butyl Acetate using esterification reaction. This soft sensor acts as a measuring element in a closed loop involving a PI controller for the direct control of the RDC’s product concentration. The RNN acts as a dynamic network, which works on the sequential input data and output data with a recurrent connection. While using the RNN based soft sensor in the open loop, it has been observed that the sensor estimated the composition of butyl acetate in the bottoms with such an accuracy that it can be used for the control purpose. Closed loop results demonstrated that the system has been showing precise controlled results and soft sensor is showing small prediction Mean Square Error (MSE) when disturbances in feed flow rate and set point changes are introduced.

Download Full-text

Control of magnetic levitation system using recurrent neural network-based adaptive optimal backstepping strategy

Transactions of the Institute of Measurement and Control ◽

10.1177/0142331220911821 ◽

2020 ◽

Vol 42 (13) ◽

pp. 2382-2395

Author(s):

Armita Fatemimoghadam ◽

Hamid Toshani ◽

Mohammad Manthouri

Keyword(s):

Neural Network ◽

Recurrent Neural Network ◽

Optimization Problem ◽

Closed Loop ◽

Magnetic Levitation ◽

Backstepping Control ◽

Loop System ◽

Closed Loop System ◽

Levitation System ◽

Magnetic Levitation System

In this paper, a novel approach is proposed for adjusting the position of a magnetic levitation system using projection recurrent neural network-based adaptive backstepping control (PRNN-ABC). The principles of designing magnetic levitation systems have widespread applications in the industry, including in the production of magnetic bearings and in maglev trains. Levitating a ball in space is carried out via the surrounding attracting or repelling magnetic forces. In such systems, the permissible range of the actuator is significant, especially in practical applications. In the proposed scheme, the procedure of designing the backstepping control laws based on the nonlinear state-space model is carried out first. Then, a constrained optimization problem is formed by defining a performance index and taking into account the control limits. To formulate the recurrent neural network (RNN), the optimization problem is first converted into a constrained quadratic programming (QP). Then, the dynamic model of the RNN is derived based on the Karush-Kuhn-Tucker (KKT) optimization conditions and the variational inequality theory. The convergence analysis of the neural network and the stability analysis of the closed-loop system are performed using the Lyapunov stability theory. The performance of the closed-loop system is assessed with respect to tracking error and control feasibility.

Download Full-text

Synthesis of n-butyl acetate via reactive distillation column using Candida Antarctica lipase as catalyst

Bioprocess and Biosystems Engineering ◽

10.1007/s00449-019-02250-2 ◽

2019 ◽

Vol 43 (4) ◽

pp. 593-604

Author(s):

Honghai Wang ◽

Wenjing Liu ◽

Liya Gao ◽

Yifan Lu ◽

Erxuan Chen ◽

...

Keyword(s):

Distillation Column ◽

Butyl Acetate ◽

Reactive Distillation ◽

Candida Antarctica ◽

Candida Antarctica Lipase

Download Full-text

Model predictive control and neural network predictive control of TAME reactive distillation column

Chemical Engineering and Processing - Process Intensification ◽

10.1016/j.cep.2012.05.003 ◽

2012 ◽

Vol 59 ◽

pp. 9-21 ◽

Cited By ~ 30

Author(s):

Neha Sharma ◽

Kailash Singh

Keyword(s):

Neural Network ◽

Model Predictive Control ◽

Predictive Control ◽

Distillation Column ◽

Reactive Distillation ◽

Neural Network Predictive Control

Download Full-text

Predictions for Start-Up Processes of Reactive Distillation Column via Artificial Neural Network

Chemical Engineering & Technology ◽

10.1002/ceat.200500345 ◽

2006 ◽

Vol 29 (6) ◽

pp. 744-749 ◽

Cited By ~ 3

Author(s):

H.-X. Wu ◽

Z.-G. Tang ◽

H. Hu ◽

C. Quan ◽

H.-H. Song ◽

...

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Distillation Column ◽

Reactive Distillation ◽

Start Up ◽

Artificial Neural

Download Full-text

Steady-State Modelling and Simulation of a Reactive Distillation Process for n-Butyl Acetate Production Using CHEMCAD

International Journal of Engineering Research in Africa ◽

10.4028/www.scientific.net/jera.29.70 ◽

2017 ◽

Vol 29 ◽

pp. 70-80 ◽

Cited By ~ 2

Author(s):

Abdulwahab Giwa ◽

Saidat Olanipekun Giwa

Keyword(s):

Acetic Acid ◽

Steady State ◽

Mole Fraction ◽

Butyl Acetate ◽

Reactive Distillation ◽

Esterification Reaction ◽

Reflux Ratio ◽

Distillation Process ◽

Condenser Section ◽

Steady State Simulation

This work has been carried out to demonstrate the application of a process simulator known as CHEMCAD to the modelling and the simulation of a reactive distillation process used for the production of n-butyl acetate, with water as the by-product, from the esterification reaction between acetic acid and n-butanol. The esterification reaction, which is generally an equilibrium type, was modelled as two kinetic reaction types in the reaction section of the column used, which had 17 stages with the middle section (stages 6 – 12) being the reaction section. A reflux ratio of 3 and reboiler duty of 78 kJ/min as well as 30 mL/min of each of the reactants with 99% molar purity were used for the simulation of the column. The results obtained revealed that the developed model was a valid one because there was a very good agreement between the results and the theoretical knowledge of a distillation column based on the fact that the desired (which was the heavy) product (n-butyl acetate) was found to have the highest mole fraction in the bottom section of the column while the by-product of the process (water) was discovered to have a mole fraction higher than that of n-butyl acetate in the top (condenser) section of the column. Therefore, CHEMCAD has been applied to the steady-state simulation of the reactive distillation process used for the production of n-butyl acetate from the esterification reaction of acetic acid and n-butanol successfully.

Download Full-text

Forecasting root-zone electrical conductivity of nutrient solutions in closed-loop soilless cultures using a recurrent neural network

Acta Horticulturae ◽

10.17660/actahortic.2020.1271.39 ◽

2020 ◽

pp. 287-292

Author(s):

T. Moon ◽

T.I. Ahn ◽

J.E. Son

Keyword(s):

Neural Network ◽

Electrical Conductivity ◽

Recurrent Neural Network ◽

Closed Loop ◽

Root Zone ◽

Nutrient Solutions

Download Full-text

Stem Control of a Sliding-Stem Pneumatic Control Valve Using a Recurrent Neural Network

Advances in Artificial Neural Systems ◽

10.1155/2013/410870 ◽

2013 ◽

Vol 2013 ◽

pp. 1-7 ◽

Cited By ~ 2

Author(s):

Mohammad Heidari ◽

Hadi Homaei

Keyword(s):

Neural Network ◽

Recurrent Neural Network ◽

Neural Control ◽

Closed Loop ◽

Control Valve ◽

Superior Performance ◽

Pneumatic Control ◽

Response Characteristics ◽

Control Scheme ◽

Simulation Results

This paper presents a neural scheme for controlling an actuator of pneumatic control valve system. Bondgraph method has been used to model the actuator of control valve, in order to compare the response characteristics of valve. The proposed controller is such that the system is always operating in a closed loop, which should lead to better performance characteristics. For comparison, minimum- and full-order observer controllers are also utilized to control the actuator of pneumatic control valve. Simulation results give superior performance of the proposed neural control scheme.

Download Full-text