Neural Network Based Model Predictive Control of Batch Extractive Distillation Process for Improving Purity of Acetone

Daosud, Wachira; Jariyaboon, Kosit; Kittisupakorn, Paisan; Hussain, Mohd Azlan

doi:10.4186/ej.2016.20.1.47

Cited by 11 publications

(3 citation statements)

References 14 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Combining model predictive control with neural networks can fully leverage the advantages of both to improve control performance and adaptability. Daosud et al 147 used water as a solvent to enhance the purity of acetone in a semicontinuous mode. A dynamic optimization strategy was applied to determine the composition curve of the acetone distillate to maximize the weight of the distillate product, i.e., acetone.…”

Section: ■ Dynamic Controlmentioning

confidence: 99%

Design and Multiple Performance Evaluation of Green Sustainable Process for Azeotropes Separation via Extractive Distillation

Zhong,

Cheng,

Dai

et al. 2023

ACS Sustainable Chem. Eng.

View full text Add to dashboard Cite

Multicomponent liquid mixtures, particularly azeotropes, are extensively utilized in the chemical, petroleum, pharmaceutical, and other processing industries. Energy-saving and efficient separation of azeotropes holds significant value for the design and development of sustainable industrial processes. Extractive distillation (ED) has consistently played a pivotal role in azeotrope separation. We offer a broad and comprehensive review that encompasses recent progress in multiple aspects of ED, including the screening of entrainers, process design, enhancement schemes, dynamic control strategies, and environmental assessment. Initially, we delved into the application of quantum chemistry calculations and molecular dynamics simulation for screening suitable entrainers. We then elucidate the design principles and forms of two distinct types of ED processes. Subsequently, we explore the intensification mechanisms of the ED process through coupling mechanisms, such as heat integration and the combination of ED with other distillation processes. We also summarize the recent improvements in dynamic control strategies for various ED processes. Lastly, we evaluate various aspects of ED from the perspectives of environmental impact, economic viability, and exergy analysis. This study investigates the challenges, prospects, and emerging trends of ED technology for the separation of multicomponent azeotropes.

show abstract

Section: ■ Dynamic Controlmentioning

confidence: 99%

Design and Multiple Performance Evaluation of Green Sustainable Process for Azeotropes Separation via Extractive Distillation

Zhong,

Cheng,

Dai

et al. 2023

ACS Sustainable Chem. Eng.

View full text Add to dashboard Cite

show abstract

“…The ability to approximate complex nonlinear relationships from process data without prior knowledge of the model structure makes neural network very attractive to the classical modeling techniques [7]. Daosud et al improved the purity of acetone using neural network model for model based control algorithm [8]. Kittisupakorn et al applied neural network model for the prediction of the concentration profile of a hydrochloric acid for hydrochloric acid recovery process and used neural network as a model in control algorithm for a steel pickling process [9].…”

Section: Introductionmentioning

confidence: 99%

Improving of Crystal Size Distribution Control Based on Neural Network-Based Hybrid Model for Purified Terephthalic Acid Batch Crystallizer

Kittisupakorn¹,

Somsong²,

Hussain³

et al. 2017

Self Cite

View full text Add to dashboard Cite

Abstract. A main difficult task in batch crystallization is to control the size distribution of crystal products. Complexity and highly nonlinear dynamic behavior directly affect to model-based control strategies which heavily depend on the rigorous knowledge of crystallization. In this work, neural network-based model predictive control and inverse neural network control strategies are proposed and integrated with an optimization based on neural network-based hybrid model to control temperatures of a purified terephthalic acid batch crystallizer. A neural network-based hybrid model of the batch crystallizer is developed to provide nonlinear dynamic responses used in optimization algorithm for finding an optimal temperature profile related to the quality of a crystal product. Then, the obtained optimal profile is used as set points of the proposed control strategies for improving the crystal product quality. The performances and robustness of the proposed controllers are evaluated in several cases such as for set point tracking and plant/model mismatches. Simulation results show that the neural network-based model predictive control gives the best control performance among the inverse neural network control and a conventional PID controller in all cases.

show abstract

“…This makes soft computing technique ideal for estimating usability of CBSS, as soft computing deals with many uncertainties [5]. Different soft computing technique has been used by various researchers for different purposes [5,6,7]. In this paper, proposed model is used to measure the usability by using two different fuzzy techniques i.e., centroid and bisector method in MATLAB.…”

Section: Introductionmentioning

confidence: 99%

Proposal and Validation of Usability Model for Component Based Software System

Agarwal¹,

Dubey²,

Tiwari³

2017

View full text Add to dashboard Cite

Increasing demand of rapid and cost effective development of software system has increased the demand of Component Based Software Engineering (CBSE). In CBSE, software system is developed by using existing components. These components can be in-house components or third party components. To develop a Component Based Software System (CBSS), it is important to select the suitable component in such a manner that the components of the software system do not affect each other. To increase the acceptance of the CBSS among the users and the market value of the software industries, it is important to increase the usability of the CBSS. Several usability models have been proposed for traditional and objectoriented software system (OOSS), but there is no usability model for CBSS. Existing traditional and objectoriented models can't be perfectly suitable for CBSS because of the unique characteristics of the components. This paper presents a usability model (UMCBSS) for CBSS. The proposed usability model is based on most significant usability factors. These factors are analysed from CBSS quality models. With the help of proposed model, usability is evaluated by using two different techniques i.e., centroid method and bisector method in MATLAB. Experimental results are also validated by using Center of Gravity (COG) and Mean-Max method. With the help of the proposed model, developers of the CBSS will be able to measure the usability of CBSS and to remove the usability flaws from the software system.

show abstract

Neural Network Based Model Predictive Control of Batch Extractive Distillation Process for Improving Purity of Acetone

Cited by 11 publications

References 14 publications

Design and Multiple Performance Evaluation of Green Sustainable Process for Azeotropes Separation via Extractive Distillation

Design and Multiple Performance Evaluation of Green Sustainable Process for Azeotropes Separation via Extractive Distillation

Improving of Crystal Size Distribution Control Based on Neural Network-Based Hybrid Model for Purified Terephthalic Acid Batch Crystallizer

Proposal and Validation of Usability Model for Component Based Software System

Contact Info

Product

Resources

About