Review of Artificial Neural Network and Its Application Research in Distillation

Sun, Jing; Tang, Qi

doi:10.9734/jerr/2021/v21i317451

Cited by 7 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A network with a small central layer is used to reconstruct highdimensional input vectors [12], which has led to a boom in the application of deep learning in various scenarios. So far, ANN has been successfully applied to intelligent driving [13][14][15], aerospace [16,17], signal processing [18][19][20], process control and optimization [21][22][23], safety protection [24][25][26], image processing [27][28][29], forest pest protection [30,31], time series forecasting [32][33][34] and so on.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Catalyst Optimization Design Based on Artificial Neural Network

Sun

2022

AJRCoS

View full text Add to dashboard Cite

Artificial neural network (ANN) has the characteristics of self-adaptation, self-learning, parallel processing and strong nonlinear mapping ability. Compared with traditional experimental analysis modeling, ANN has obvious advantages in dealing with multivariable nonlinear complex relationships in the process of industrial catalyst design. In the face of the complex structure of catalyst, the unclear reaction mechanism and conditions, the use of neural network for small-scale experimental data analysis can save the time and energy invested in large-scale experimental research and obtain more perfect results in catalyst formulation optimization and condition selection. This paper summarizes the development of artificial neural network. The application principle, construction method and research progress of BP artificial neural network model in catalyst optimization design are summarized and analyzed. The development and innovation of artificial neural network in the future, as well as its continuous application and accumulation, will provide a powerful tool for the research of catalyst design and optimization in the future.

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

Catalyst Optimization Design Based on Artificial Neural Network

Sun

2022

AJRCoS

View full text Add to dashboard Cite

show abstract

“…At the same time, by adding a so-called hidden layer to the neural network, the back propagation algorithm also solves the XOR problem that the perceptron cannot solve. BP neural network model is the most widely used artificial neural network model in modern neural network as prediction [15,16].…”

Section: Fig 1 the Structure Of Artificial Neural Networkmentioning

confidence: 99%

Research Progress of Chemical Process Control and Optimization Based on Neural Network

Zhao

2021

JERR

View full text Add to dashboard Cite

Chemical process is usually regarded as a comprehensive system and optimized as a whole because of the interaction and restriction between its operation units. The classical control technology is limited to the control system dealing with single variable. Artificial neural network (ANN) is an algorithmic mathematical model that imitates the behavioral characteristics of animal neural networks for information processing. It has the advantages of nonlinear, large-scale, and strong parallel processing capabilities, as well as robustness. This article summarizes the basic principles and development history of ANN, and analyzes the research progress of chemical process control and optimization based on artificial neural networks in recent years.

show abstract

“…[49][50][51][52][53] Artificial neural network (ANN) is a network system constructed by imitating the interconnection between neurons in the human brain, which can achieve approximation to any nonlinear mapping through learning. 54 It has fault tolerance and parallel information processing functions, and has been widely used in intelligent control, 55,56 signal processing, 57,58 chemical process optimization [59][60][61][62] and so on. There are many training algorithms that can be used, among which the typical ones are the back-propagation (BP) algorithm and Levenberg-Marquardt algorithm.…”

Section: Introductionmentioning

confidence: 99%

Synthesis of isoamyl hexanoate catalyzed by deep eutectic solvent based on benzyltrimethylammonium chloride:RSMandANNoptimization and kinetics

Sun

Zeng

et al. 2023

J of Chemical Tech & Biotech

View full text Add to dashboard Cite

BackgroundIsoamyl hexanoate is a widely used edible spice. In this paper, the process and kinetics of the esterification of hexanoic acid and isoamyl alcohol to isoamyl hexanoate catalyzed by deep eutectic solvents (DESs) were studied. Several kinds of DESs (BTMAC‐zPTSA) were prepared from benzyltrimethylammonium chloride (BTMAC) and p‐toluenesulfonic acid monohydrate (PTSA) with a molar ratio of z. The synthesis process of isoamyl hexanoate was optimized by response surface methodology and artificial neural network. The effects of process conditions such as the kind and load of catalyst, alcohol/acid ratio and reaction temperature were studied. In the temperature range of 338.15 to 368.15 K, BTMAC‐1.2PTSA was selected as the catalyst, and then the kinetic data and chemical equilibrium composition of the esterification of hexanoic acid with isoamyl alcohol were determined.ResultsAfter optimizing the synthesis process of isoamyl hexanoate using response surface methodology and artificial neural network, the conversion rate of hexanoic acid increased to 92.15%. The esterification reaction kinetics were described using a pseudo‐homogeneous model based on activity, with an average relative deviation of 1.9% and activation energy of 25.79 kJ mol−1. The catalytic performance of catalyst BTMAC‐1.2PTSA remains good after five cycles of use.ConclusionThe established kinetic model has a good predictive effect on the kinetic data for the synthesis of isoamyl hexanoate. The catalyst BTMAC‐1.2PTSA has good stability and recyclability, and has the potential to replace traditional catalysts in the production of isoamyl hexanoate. © 2023 Society of Chemical Industry.

show abstract

Review of Artificial Neural Network and Its Application Research in Distillation

Cited by 7 publications

References 28 publications

Catalyst Optimization Design Based on Artificial Neural Network

Catalyst Optimization Design Based on Artificial Neural Network

Research Progress of Chemical Process Control and Optimization Based on Neural Network

Synthesis of isoamyl hexanoate catalyzed by deep eutectic solvent based on benzyltrimethylammonium chloride:RSMandANNoptimization and kinetics

Contact Info

Product

Resources

About