Performance prediction of disc and doughnut extraction columns using bayes optimization algorithm-based machine learning models

Su, Zhenning; Wang, Yong; Tan, Boren; Cheng, Quanzhong; Duan, Xiaofei; Xu, Dongbing; Liu, Tian; Qi, Tao

doi:10.1016/j.cep.2022.109248

Cited by 8 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where x denotes a set of hyperparameter values in the domain X, and x * is the hyperparameter value set that maximises the performance, i.e., the output of the objective function f [45]. Hyperparameters are tuned by the Expected-Improvement-Per-Second Plus, which provides the fastest speed of the convergence criterion as well as prevents overexploiting possible ranges of hyperparameter domains from being illuded by the local maximum [46].…”

Section: Hyperparameter Tuning With Bayesian Optimisation Algorithmmentioning

confidence: 99%

The Design of a Piecewise-Integrated Composite Bumper Beam with Machine-Learning Algorithms

Ham,

Ji,

Cheon

2024

Materials

View full text Add to dashboard Cite

In the present study, a piecewise-integrated composite bumper beam for passenger cars is proposed, and the design innovation process for a composite bumper beam regarding a bumper test protocol suggested by the Insurance Institute for Highway Safety is carried out with the help of machine learning models. Several elements in the bumper FE model have been assigned to be references in order to collect training data, which allow the machine learning model to study the method of predicting loading types for each finite element. Two-dimensional and three-dimensional implementations are provided by machine learning models, which determine the stacking sequences of each finite element in the piecewise-integrated composite bumper beam. It was found that the piecewise-integrated composite bumper beam, which is designed by a machine learning model, is more effective for reducing the possibility of structural failure as well as increasing bending strength compared to the conventional composite bumper beam. Moreover, the three-dimensional implementation produces better results compared with results from the two-dimensional implementation since it is preferable to choose loading-type information, which is achieved from surroundings when the target elements are located either at corners or junctions of planes, instead of using information that comes from the identical plane of target elements.

show abstract

Section: Hyperparameter Tuning With Bayesian Optimisation Algorithmmentioning

confidence: 99%

The Design of a Piecewise-Integrated Composite Bumper Beam with Machine-Learning Algorithms

Ham,

Ji,

Cheon

2024

Materials

View full text Add to dashboard Cite

show abstract

“…where 𝒙 denotes a set of hyperparameter values in the domain 𝑿, and 𝒙 * is the set of hyperparameters that maximises the performance, i.e., the output of the objective function 𝒇 [42]. Hyperparameters were tuned by the Expected-Improvement-Per-Second Plus, which provided fastest speed of the convergence criterion as well as prevented overexploiting possible ranges of hyperparameter domains from being illuded by the local maximum [43].…”

Section: Hyperparameter Tuning With Bayesian Optimisation Algorithmmentioning

confidence: 99%

The Design of Piecewise Integrated Composite Bumper Beam With Machine Learning Algorithm

Ham¹,

Cheon²

2023

Preprint

View full text Add to dashboard Cite

In the present study, piecewise integrated composite (PIC) bumper beam for passenger cars was proposed and design optimisation process for composite bumper beam against IIHS test was carried out with the help of machine learning. Several elements in IIHS bumper FE model have been assigned to be references, in order to collect training data which, allow the machine learning model to study the method of predicting loading types of each finite element. 2-D and 3-D implementations were provided by machine learning models, which determined stacking sequences of each finite element in PIC bumper beam. It was found that the PIC bumper beam, which was designed by machine learning model has direct impact on reducing the possibility of failure as well as increasing bending strength effectively than conventional composite bumper beam. Moreover, 3-D implementation produced better results compared with 2-D implementation since it was preferable to choose loading type information which was achieved from surroundings when the target elements were located either at corner or junction of planes instead of using information came from the same plane of target.

show abstract

“…Among of suitable methods for this purpose is liquid-liquid extraction (LLE), which is a key operation in many separation processes in chemical, pharmaceutical, environmental, food, nuclear, and hydrometallurgy industries to recover materials in dilution. [13][14][15][16][17][18][19][20][21][22] The primary extracts obtained from the traditional extraction processes such as percolation and HD can be used as feed for LLE columns to separate better the active ingredients from herbs. HD is one of these traditional techniques for extracting the active ingredients from herbs, which has become an interesting field of study.…”

Section: Introductionmentioning

confidence: 99%

“…Among of suitable methods for this purpose is liquid–liquid extraction (LLE), which is a key operation in many separation processes in chemical, pharmaceutical, environmental, food, nuclear, and hydrometallurgy industries to recover materials in dilution. [ 13–22 ]…”

Section: Introductionmentioning

confidence: 99%

Mass transfer performance of pulsed disk and doughnut column (PDDC) in the extraction of active ingredients in peppermint extract obtained by hot percolation

Hosseini,

Bahmanyar,

Rahimpour

et al. 2024

Can J Chem Eng

View full text Add to dashboard Cite

The active ingredients in peppermint are widely used in the pharmaceutical, food, cosmetic, and other industries. The traditional methods for producing peppermint extract through hydrodistillation (HD) and percolation are long process with low efficiency. The aim of this study is the improvement of the extraction performance and the efficiency of the extract obtained from hot percolation via pulsed disk and doughnut columns (PDDC), which is one of the most important pieces of liquid–liquid extraction (LLE) equipment. Peppermint extract was used as the continuous phase in the PDDC. n‐Hexane was considered as the dispersed phase in this column. In this study, the effects of three operating parameters were investigated, including the pulse intensity, continuous phase height, and dispersed phase flow rate, on the extraction efficiency of active ingredients in peppermint. The response surface method (RSM) was used to investigate the effect of these parameters on the extraction efficiency. The efficiency of this column in the extracting of active ingredients from peppermint was measured by UV–vis spectrophotometry, via the absorption rate of the main active ingredients of peppermint (menthol) in the samples, and the efficiency was 75% on average. The experimental and theorical of dispersed phase mass transfer coefficient were evaluated and compared. The results showed that the PDDC improved the extraction and mass transfer. By increasing the flow rate of the dispersed phase and the height of the continuous phase, the extraction efficiency and the mass transfer coefficient were increased.

show abstract

Performance prediction of disc and doughnut extraction columns using bayes optimization algorithm-based machine learning models

Cited by 8 publications

References 31 publications

The Design of a Piecewise-Integrated Composite Bumper Beam with Machine-Learning Algorithms

The Design of a Piecewise-Integrated Composite Bumper Beam with Machine-Learning Algorithms

The Design of Piecewise Integrated Composite Bumper Beam With Machine Learning Algorithm

Mass transfer performance of pulsed disk and doughnut column (PDDC) in the extraction of active ingredients in peppermint extract obtained by hot percolation

Contact Info

Product

Resources

About