Case-study of a flowsheet simulation using deep-learning process models for multi-objective optimization of petrochemical production plants

Zapf, Fabian; Wallek, Thomas

doi:10.1016/j.compchemeng.2022.107823

Cited by 6 publications

(8 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In chemical industries, it is applied to optimize processes. Zapf F. et al (2022) [ 41 ] proposed the implementation of the multi-objective optimization of the naphtha catalytic reformer. In [ 42 , 43 ], the authors carried out similar multi-objective cases for a non-conventional naphtha catalytic reformer where aromatics, hydrogen, and aniline production were maximized.…”

Section: Theoretical Considerations On Injection Molding Process Opti...mentioning

confidence: 99%

Optimization of the Reduction of Shrinkage and Warpage for Plastic Parts in the Injection Molding Process by Extended Adaptive Weighted Summation Method

et al. 2022

View full text Add to dashboard Cite

The consumer market has changed drastically in recent times. Consumers are becoming more demanding, and many companies are competing to be market leaders. Therefore, companies must reduce rejects and minimize their operating costs. One problem that arises in producing plastic parts is controlling deformation, mainly in the form of shrinkage due to the material and warpage associated with the geometry of the parts. This work presents a novel extended adaptive weighted sum method (EAAWSM: Extended Adaptive Weighted Summation Method) integrated into a Pareto front model. The performance of this model is evaluated against three other conventional optimization methods—Taguchi–Gray (TG), Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), and Model Optimization by Genetic Algorithm (MOGA)—and compared with EAAWSM. Two response variables and three input factors are considered to be analyzed: material melting temperature, mold temperature, and filling time. Subsequently, the performance is compared and its behavior observed using Moldflow® simulation. The results show that with the EAAWSM method, the shrinkage is 15.75% and the warpage is 3.847 mm, regarding the manufacturing process parameters of a plastic part. This proposed deterministic model is easy to use to optimize two or more output variables, and its results are straightforward and reliable.

show abstract

Section: Theoretical Considerations On Injection Molding Process Opti...mentioning

confidence: 99%

Optimization of the Reduction of Shrinkage and Warpage for Plastic Parts in the Injection Molding Process by Extended Adaptive Weighted Summation Method

et al. 2022

View full text Add to dashboard Cite

show abstract

“…They also conducted a comparative economic analysis based on 200,000 tonne per year plant production and concluded that process integration techniques are able to significantly reduce costs. [34] Zapf and Wallek [35] created process models based on machine learning using process data, and connected them to an overall process flowsheet. Their approach provided perfect numerical stability for subsequent multiobjective optimization.…”

Section: Introductionmentioning

confidence: 99%

“…They also indicated that developing datadriven grey-box models could be further studied and extended to chemical reactors. [35] Zendehboudi et al studied the applications of hybrid models (HMs) in petroleum, gas, chemical processes, and energy systems and reviewed sub-models, hybridization strategies, structural designs, screening criteria, and new directions in hybrid modelling with a focus on these industries. They pointed out that complex processes related to chemical and energy systems require advanced mathematical tools because of the mathematical complexities and lack of knowledge about these processes.…”

Section: Introductionmentioning

confidence: 99%

“…Zapf and Wallek [ 35 ] created process models based on machine learning using process data, and connected them to an overall process flowsheet. Their approach provided perfect numerical stability for subsequent multi‐objective optimization.…”

Section: Introductionmentioning

confidence: 99%

“…They applied black‐box and grey‐box models and compared them to the well‐established LP approach. Zapf and Wallek [ 35 ] used real‐world measurement data from a refinery to illustrate their proposed methodology. This refinery comprised a distillation unit, a hydrotreater, a reformer, and an ethylene plant.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Analysis of the high‐pressure steam import behaviour of an integrated ethylene oxide/ethylene glycol petrochemical plant under different production scenarios

Sharifara,

Abbaspour,

Saraei

2023

Can J Chem Eng

View full text Add to dashboard Cite

Integrated ethylene oxide/ethylene glycols (EO/EG) plants are prominent energy consumers in the petrochemical sector, particularly concerning high‐pressure steam (HPS) usage which holds the potential for substantial energy savings. This study focuses on an unexplored territory: Examining the impact of EO catalyst type, selectivity, and glycols production capacity on HPS import in a plant in the Pars Special Economic Energy Zone (PSEEZ). Utilizing Python3 for data preprocessing and ordinary least squares linear regression analysis, we evaluate how varying catalyst loads and production scenarios influence HPS import. Regression models are created, encompassing normal and efficient HPS import scenarios, yielding positive outcomes in terms of correlation, mean error percentage, and R2 analysis. Comparing normal and efficient HPS import models highlights potential savings, uncovering opportunities to conserve between 45 and over 200 tonnes per day of HPS. We also explore the plant's HPS behaviour under 1% selectivity and production capacity reductions. Notably, catalyst activity decline markedly escalates HPS import for hybrid catalysts, while selectivity decline decreases HPS import for high‐activity catalysts. The models demonstrate that HPS import is ~150 tonnes per day more sensitive to a 1% change in selectivity compared to production capacity. Moreover, when comparing high activity and hybrid catalyst scenarios in normal and efficient cases, the most substantial HPS import difference arises under conditions of low selectivity, amounting to nearly 200 tonnes per day. Our methodology applies to other EO/EG plants. It is incorporated into our plant's energy management system, enabling continuous monitoring of steam import behaviour relative to catalyst and plant performance.

show abstract

Transparent AI-assisted chemical engineering process: Machine learning modeling and multi-objective optimization for integrating process data and molecular-level reaction mechanisms

Xu,

Wang,

Zhang

et al. 2024

Journal of Cleaner Production

View full text Add to dashboard Cite

Case-study of a flowsheet simulation using deep-learning process models for multi-objective optimization of petrochemical production plants

Cited by 6 publications

References 31 publications

Optimization of the Reduction of Shrinkage and Warpage for Plastic Parts in the Injection Molding Process by Extended Adaptive Weighted Summation Method

Optimization of the Reduction of Shrinkage and Warpage for Plastic Parts in the Injection Molding Process by Extended Adaptive Weighted Summation Method

Analysis of the high‐pressure steam import behaviour of an integrated ethylene oxide/ethylene glycol petrochemical plant under different production scenarios

Transparent AI-assisted chemical engineering process: Machine learning modeling and multi-objective optimization for integrating process data and molecular-level reaction mechanisms

Contact Info

Product

Resources

About