Effect of Different Parameters on WEPS Production and Thermal Behavior Prediction Using Artificial Neural Network (ANN)

Moghaddam, Amin Hedayati; Sargolzaei, Javad; Asl, M. Haghighi; Derakhshanfard, Fahimeh

doi:10.1080/03602559.2011.651243

Cited by 9 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Supporting Information for this article can be found under DOI: 10.1002/ceat.202000347. This section includes additional references to primary literature relevant for this research 63–74.…”

Section: Supporting Informationmentioning

confidence: 99%

Experimental Optimization and Modeling of Supercritical Fluid Extraction of Oil from Pinus gerardiana

2021

View full text Add to dashboard Cite

The influence of different temperatures, pressures, and flow rates on the supercritical fluid extraction (SFE) of oil from Pinus gerardiana was investigated. Extraction was designed using the Box‐Behnken design and artificial neural network. Furthermore, a mathematical model of broken and intact cells was applied to consider mass transfer kinetics of extracted natural materials. The experimental oil extraction was performed by Soxhlet and supercritical carbon dioxide methods and the yield and composition of the obtained oils was compared. Although the yield of the SFE process was lower than that of the Soxhlet extraction, the SFE presented the advantage of shorter extraction time and lower temperatures. Also, the chemical compositions of the obtained oils from Soxhlet and SFE processes were the same.

show abstract

Section: Supporting Informationmentioning

confidence: 99%

Experimental Optimization and Modeling of Supercritical Fluid Extraction of Oil from Pinus gerardiana

2021

View full text Add to dashboard Cite

show abstract

“…This model was used to optimize the performance of an alkylation reactor. Moghaddam et al 20 investigated the differential thermal analysis and thermal behavior prediction of water expandable polystyrene using an artificial neural network. Their results showed good agreement between the predicted thermal behavior and actual values.…”

Section: Introductionmentioning

confidence: 99%

Study on the processes and warpage of double‐injection‐molded parts containing PP recycled materials

Li,

Wang,

Xie

et al. 2024

Polymer Engineering & Sci

View full text Add to dashboard Cite

Double‐injection molding involves the use of two injection units, A and B, which can combine two different plastics into one part in a single injection molding process. Double‐injection molding can promote the recycling of plastic waste as well as improve the performance and dull appearance of plastic products made from recycled materials. However, the warpage of parts is a significant challenge in double‐injection molding. Warpage is significantly affected by the properties of the recycled material and injection molding process. In this study, the relationship between the warpage of double‐injection‐molded parts using raw and recycled materials was studied through uniform design experiments. To investigate the processes and warpage, the material was recycled several times, and its properties were tested. A regression model was established to describe the quantitative relationship between the important parameters and warpage. The number‐average molecular weight and weight‐average molecular weight exhibited the largest decrease after the first recycling cycle with a 21.11% and 41.11% decrease, respectively. The melting temperature decreased from 164.61 to 159.35°C, and the crystallinity did not change significantly. The processing parameters varied with the change in the properties of PP recycled materials, with the melt temperature decreased from 225 to 210°C. In addition, the number of recycling cycles and holding time for B were the most important factors influencing the warpage of double‐injection‐molded parts, followed by holding time for A and melt temperature for A. Warpage can be reduced by increasing holding times B and A. The experimental results provide important data for reducing the warpage of double‐injection‐molded parts with recycled materials.Highlights Double‐injection‐molded parts containing recycled materials were prepared. Recycling enhanced the filling capacity of polypropylene. The regression model of warpage with variables was established. Warpage can be improved by adjusting processes and materials.

show abstract

“…In regression problems, artificial neural networks (ANN) can discover complex input and output relationships. Therefore, these networks have been used in various fields of science and engineering to model the relationship between input and continuous responses [31] - [34]. Therefore, this tool can be used to predict the combustion performance of different fuels in terms of operating factors.…”

Section: Introductionmentioning

confidence: 99%

Development of Machine Learning Models for Studying the Premixed Turbulent Combustion of Gas-To-Liquids (GTL) Fuel

Sadeq,

Hedayati,

Sleiti

et al. 2023

Preprint

View full text Add to dashboard Cite

Studying the spatial and temporal evolution in turbulent flames represents one of the most challenging problems in the combustion community. Based on previous 3D numerical analyses, this study aims to develop data-driven Machine Learning (ML) models for predicting the flame radius evolution and turbulent flame speeds for diesel, GTL, and their 50/50 blend (by volumetric composition) under different thermodynamic and turbulence operating conditions. Two ML models were developed in this study. Model 1 predicts the variations of the flame radius with time, equivalence ratio, and turbulence intensity, whereas Model 2 predicts the variations of the turbulence flame speed with the operating parameters. The k-fold cross-validation technique is used for model training, and the developed neural network-based model is used to investigate the effects of operating parameters on the premixed turbulent flames. In addition, the possible minimum and maximum values of responses at the corresponding operating parameters are found by using a Genetic Algorithm (GA) approach. Model 1 could capture the CFD outputs with high precision at different flame radiuses and time instants with a maximum absolute error percentage of 5.46%. For Model 2, the maximum absolute error percentage was 6.58%. Overall, this study demonstrates the applicability and promising performance of the proposed ML models, which will be used in subsequent research to analyze turbulent flames a posteriori.

show abstract

Effect of Different Parameters on WEPS Production and Thermal Behavior Prediction Using Artificial Neural Network (ANN)

Cited by 9 publications

References 20 publications

Experimental Optimization and Modeling of Supercritical Fluid Extraction of Oil from Pinus gerardiana

Experimental Optimization and Modeling of Supercritical Fluid Extraction of Oil from Pinus gerardiana

Study on the processes and warpage of double‐injection‐molded parts containing PP recycled materials

Development of Machine Learning Models for Studying the Premixed Turbulent Combustion of Gas-To-Liquids (GTL) Fuel

Contact Info

Product

Resources

About