A Multi-objective optimization for batch chemical reaction Processes: The trade-off between economy and safety

Wu, Yi; Ye, Haotian; Dong, Hongguang

doi:10.1016/j.ces.2022.118231

Cited by 8 publications

(2 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the decision-making should be carried out after finding Pareto front solutions to determine the final optimal design of the EDWC and EDDWC. The TOPSIS based on geometric distance is a classical multicriteria decision analysis approach, ,− which involves the following steps: (1) All the original criteria receive tendency treatment. (2) Calculate the normalized decision matrix r .…”

Section: Methodsmentioning

confidence: 99%

Improved Multiobjective Particle Swarm Optimization Integrating Mutation and Changing Inertia Weight Strategy for Optimal Design of the Extractive Single and Double Dividing Wall Column

Sun,

Yang,

Chang

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

The extractive dividing wall column (EDWC) has received more and more attention because of the advantages of energy saving and high efficiency for separating mixtures with multiple azeotropes. Nevertheless, the optimization of the EDWC is challenging due to its highly nonlinear behaviors and inherent strong interactions caused by the decrease in the degree of freedom. This work proposes a multiobjective optimization framework that combines the particle swarm algorithm and the technique for order preference by similarity to the ideal solution to determine the optimal decision variable of the EDWC to improve economic performance. In this contribution, the particle mutation and linearly decreasing inertia weight strategies are introduced in the conventional multiobjective particle swarm optimization (MOPSO) to increase population diversity and feasible solutions for the decision-maker. The proposed optimization framework is validated through two case studies [i.e., EDWC for separating acetonitrile/N-propanol and extractive double dividing wall column (EDDWC) for separating tetrahydrofuran/methanol/water]. The results demonstrate that the improved MOPSO presents unique advantages in terms of maintaining population diversity compared to sequential iterative optimization and the genetic algorithm. Compared with the sequential iterative optimization, the total annual cost of the EDWC and EDDWC is respectively decreased by 12.34 and 36.03% via the proposed optimization strategy.

show abstract

Section: Methodsmentioning

confidence: 99%

Improved Multiobjective Particle Swarm Optimization Integrating Mutation and Changing Inertia Weight Strategy for Optimal Design of the Extractive Single and Double Dividing Wall Column

Sun,

Yang,

Chang

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

“…NSGA-II can effectively solve nonlinear optimization problems, breaking through the shortcomings of traditional multiobjective optimization methods such as the ε-constraint method, , linear programming method, and weighted sum method, which are ineffective in the absence of experience, overly dependent on initial values, and easily trapped in locally optimal solutions. The NSGA-II settings are shown in Table S9.…”

Section: Optimization Of the Pilot-scale Case Based On The Optimal K-...mentioning

confidence: 99%

Interpretable Machine Learning-Based Model to Classify and Optimize Isoperibolic Batch Reactors

Wen,

Lyu,

Zhang

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

It is crucial to classify and optimize the thermal behaviors of isoperibolic batch reactors. This article aims to construct an improved supervised machine learning-based (ML-based) model to achieve the task. First, using the minimum redundancy maximum relevance algorithm, the k-nearest neighbor (k-NN) algorithm with a feature subset consisting of 18 dimensions is selected due to the highest total recognition accuracy in 27 different ML algorithms. Additionally, a cost-sensitive learning approach and Bayesian optimization algorithm are employed to further optimize the hyper-parameters of the k-NN model. The accuracies of all data sets using the optimal k-NN model are all 99.8%, indicating that the optimal k-NN model has a superior performance and a good generalization ability. Then, two cases coupled with interpretability techniques are used to interpret the optimal k-NN model. Finally, based on the optimal k-NN model, two novel optimization frameworks (single-objective and multiobjective) are proposed to optimize the mentioned pilot-scale case, and the results prove that the optimization frameworks are reasonable and reliable.

show abstract

Artificial intelligent support model for multiple criteria decision in construction management

Son,

Khoi

2024

OPSEARCH

View full text Add to dashboard Cite

A Multi-objective optimization for batch chemical reaction Processes: The trade-off between economy and safety

Cited by 8 publications

References 48 publications

Improved Multiobjective Particle Swarm Optimization Integrating Mutation and Changing Inertia Weight Strategy for Optimal Design of the Extractive Single and Double Dividing Wall Column

Improved Multiobjective Particle Swarm Optimization Integrating Mutation and Changing Inertia Weight Strategy for Optimal Design of the Extractive Single and Double Dividing Wall Column

Interpretable Machine Learning-Based Model to Classify and Optimize Isoperibolic Batch Reactors

Artificial intelligent support model for multiple criteria decision in construction management

Contact Info

Product

Resources

About