Thermodynamics-based neural network and the optimization of ethylbenzene production process

Hang, Peng; Zhou, Leihao; Liu, Guilian

doi:10.1016/j.jclepro.2021.126615

Cited by 8 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The output variables include boiling temperature, product flow rate, supply temperature of the steam to be heated and cooled, target temperature, corresponding enthalpy change, and diameter of each section. Peng et al [46] established the improved Back Propagation neural network (BP-NN) models for the reactor and distillation column but did consider the cost of capital. Moreover, some use surrogate models to achieve multi-objective optimization of more complex distillation columns [47].…”

Section: Previous Research On Distillation Column Designmentioning

confidence: 99%

Intelligent Optimization Design of Distillation Columns Using Surrogate Models Based on GA-BP

Zhang

et al. 2023

Processes

View full text Add to dashboard Cite

The design of distillation columns significantly impacts the economy, energy consumption, and environment of chemical processes. However, optimizing the design of distillation columns is a very challenging problem. In order to develop an intelligent technique to obtain the best design solution, improve design efficiency, and minimize reliance on experience in the design process, a design methodology based on the GA-BP model is proposed in this paper. Firstly, a distillation column surrogate model is established using the back propagation neural network technique based on the training data from the rigorous simulation, which covers all possible changes in feed conditions, operating conditions, and design parameters. The essence of this step is to turn the distillation design process from model-driven to data-driven. Secondly, the model takes the minimum TAC as the objective function and performs the optimization search using a Genetic Algorithm to obtain the design solution with the minimum TAC, in which a life-cycle assessment (LCA) model is incorporated to evaluate the obtained optimized design solution from both economic and environmental aspects. Finally, the feasibility of the proposed method is verified with a propylene distillation column as an example. The results show that the method has advantages in convergence speed without sacrificing accuracy and can obtain an improved design solution with reduced cost and environmental impact. Compared with the original design using rigorous simulation, the TAC is reduced by 6.1% and carbon emission by 27.13 kgCO2/t.

show abstract

Section: Previous Research On Distillation Column Designmentioning

confidence: 99%

Intelligent Optimization Design of Distillation Columns Using Surrogate Models Based on GA-BP

Zhang

et al. 2023

Processes

View full text Add to dashboard Cite

show abstract

“…Decision tree (DT) and artificial neural network (ANN) are commonly used supervised machine learning algorithms, which can realize the mining and classification management of complex non-linear relationship datasets without causal cognition ( 19 ). Therefore, DT and ANN were used to conduct extensive research to predict air environmental quality ( 20 – 24 ), diagnostic optimization and prediction of chemical processes ( 25 – 29 ), soil and groundwater pollution prediction ( 30 – 32 ). The existing research on DT and ANN algorithms mainly focuses on two aspects.…”

Section: Introductionmentioning

confidence: 99%

Prediction Performance Comparison of Risk Management and Control Mode in Regional Sites Based on Decision Tree and Neural Network

Wang¹,

He²,

Zhang³

et al. 2022

Front. Public Health

View full text Add to dashboard Cite

The traditional risk management and control mode (RMCM) in regional sites has the defects of low efficiency, high cost, and lack of systematism. Trying to resolve these defects and explore the application possibility of machine learning, a characteristic dataset for RMCM in regional sites was established. Three decision tree (DT) algorithms (CHAID, EXHAUSTIVE CHAID, and CART) and two artificial neural network (ANN) algorithms [back propagation (BP) and radial basis function (RBF)] were implemented to predict RMCM in regional sites. The results showed that in the aspects of accuracy (ACC), precision (PRE), recall ratio (REC), and F1 value, CART–DT was superior to CHAID–DT and EXHAUSTIVE CHAID–DT (E-CHAID–DT); and BP–ANN was superior to RBF–ANN. However, CART–DT was inferior to BP–ANN in ACC, PRE, REC, and F1 value. BP–ANN model is good at non-linear mapping, and it has a flexible network structure and a low risk of over-fitting. The case study of a typical county demonstration area confirmed the extensibility of the method, and the method has great potential in RMCM prediction in regional sites in the future.

show abstract

“…Hang et al built a neural network for the reactor and distillation column of a pure-ethylene process to minimize energy consumption. The results indicated that the heating utility consumption is reduced by 55.2% . However, EB production processes have become more complicated, and researchers need to pay close attention to their modeling and optimization methods.…”

Section: Introductionmentioning

confidence: 99%

“…The results indicated that the heating utility consumption is reduced by 55.2%. 15 However, EB production processes have become more complicated, and researchers need to pay close attention to their modeling and optimization methods.…”

Section: Introductionmentioning

confidence: 99%

Multiobjective Economic-Environmental-Selectivity Optimization of the Dry Gas Based Ethylbenzene Production Process

Han

Zhao

2021

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

The ethylbenzene production process from dry gas has been an energy-intensive process that will inevitably bring about massive carbon emissions. With increasingly stringent regulations to mitigate the effect of greenhouse gas emissions, decision-makers need to make a trade-off among the objectives of environmental impact, economic benefit, and process indicators. An integrated framework combining simulation and multiobjective optimization is proposed to address this issue. The model of the dry gas based ethylbenzene production process is developed by Aspen Plus. The multiobjective optimization (MOO) model, including the profit before tax (PBT), greenhouse gas emissions (GHGs), and alkylation reaction selectivity (S AR ), is then derived considering the operational flexibility and mass and energy balance constraints. The Nondominated Sorting Genetic Algorithm II (NSGA-II) is used to solve this problem, and the three-dimensional Pareto front is obtained. The TOPSIS method is employed to select a specific solution from the Pareto front. Then, the sensitivity analysis is performed to assess the effects of the decision variables on the objectives. Compared with the original operating conditions, a substantial reduction in GHGs (23%) and a slight increase in PBT (4.1%) are achieved at the expense of specific S AR (5.3%).

show abstract

Thermodynamics-based neural network and the optimization of ethylbenzene production process

Cited by 8 publications

References 18 publications

Intelligent Optimization Design of Distillation Columns Using Surrogate Models Based on GA-BP

Intelligent Optimization Design of Distillation Columns Using Surrogate Models Based on GA-BP

Prediction Performance Comparison of Risk Management and Control Mode in Regional Sites Based on Decision Tree and Neural Network

Multiobjective Economic-Environmental-Selectivity Optimization of the Dry Gas Based Ethylbenzene Production Process

Contact Info

Product

Resources

About