Production of Low Cost Carbon-Fiber through Energy Optimization of Stabilization Process

Golkarnarenji, Gelayol; Naebe, Minoo; Badii, Khashayar; Milani, Abbas S.; Jazar, Reza N.; Khayyam, Hamid

doi:10.3390/ma11030385

Cited by 28 publications

(11 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These comparisons suggested that a SVR model was a better prediction model than an ANN model, a consistent conclusion in both the training stage and the validation stage. The limited number of data caused the unexpected low performance of the ANN model [32][33][34] Therefore, the developed model can be used for estimating the number of impeller revolution for pharmaceutical formulation across different wet-mixing machines. This conclusion was consistent with the suggestion in different applications and highlighted the possible mathematical relationship between the number of impeller revolution, the properties of excipients, and the parameters of machines.…”

Section: Support Vector Regression (Svr Model)mentioning

confidence: 99%

Artificial Neural Network and Support Vector Regression Modeling for Prediction of Mixing Time in Wet Granulation

2021

View full text Add to dashboard Cite

Purpose Every successful pharmaceutical product requires a rapid and reliable scale-up process from small laboratory quantities to a large commercial production to ensure the qualities of products. Despite best efforts, a pharmaceutical company must incur losses in material costs and working-hours before achieving optimal process parameters. One possible approach to shorten this tedious process is to leverage knowledge and experience using a computational algorithm that predicts the process parameters using related data. Method This study aimed to demonstrate the approach of embedded successful material attributes and process parameters of wet granulation as inputs into an artificial neural network (ANN) model and support vector regression (SVR) model to predict the total number of the impeller revolution for dry mixing and wet massing to produce the granules with the same qualities. ResultsThe SVR model performed better for prediction with RMSEs of 3.2552-4.0066. Using the SVR model using Gaussian kernel, which had the least RMSE, in the training stage and validation stage gave the values of MAPE of 17.12% and 12.32%, respectively. Conclusion The model can be implemented for the prediction of the number of impeller revolution by using the proposed parameters.

show abstract

Section: Support Vector Regression (Svr Model)mentioning

confidence: 99%

Artificial Neural Network and Support Vector Regression Modeling for Prediction of Mixing Time in Wet Granulation

2021

View full text Add to dashboard Cite

show abstract

“…To make a reliable statistical test under small sample size, Design of Experiments (DOE) methods have been proposed, such as Response Surface, Taguchi and Factorial [9]. Development of DOE based on Taguchi methods to reduce industrial experimental tests requires reliable data modelling [10,11]. In some other industrial applications, large-scale data is produced, and sophisticated machine learning needs to be employed to process the data.…”

Section: Machine Learning Techniques To Model Limited or Big Datamentioning

confidence: 99%

A Novel Hybrid Machine Learning Algorithm for Limited and Big Data Modeling With Application in Industry 4.0

et al. 2020

Self Cite

View full text Add to dashboard Cite

To meet the challenges of manufacturing smart products, the manufacturing plants have been radically changed to become smart factories underpinned by industry 4.0 technologies. The transformation is assisted by employment of machine learning techniques that can deal with modelling both big or limited data. This manuscript reviews these concepts and present a case study that demonstrates the use of a novel intelligent hybrid algorithms for Industry 4.0 applications with limited data. In particular, an intelligent algorithm is proposed for robust data modelling of nonlinear systems based on input-output data. In our approach, a novel hybrid data-driven combining the Group-Method of Data-Handling and Singular-Value Decomposition is adapted to find an offline deterministic model combined with Pareto multi-objective optimization to overcome the overfitting issue. An Unscented-Kalman-Filter is also incorporated to update the coefficient of the deterministic model and increase its robustness against data uncertainties. The effectiveness of the proposed method is examined on a set of real industrial measurements. INDEX TERMS Industry 4.0; Big data modelling; Limited data modelling, Multi-objective optimization. NOMENCLATURE CNN

show abstract

“…[14,15] Such a long time not only results in low efficiency but also large energy consumption. [16] In addition, with the conventional heating method, the nonuniform thermal field in the PAN fiber may cause serious skin-core structure and affect the performance of the final carbon fiber. [17] Most recently, efforts have been devoted to making use of the microwave for the thermal stabilization of PAN precursors to avoids these problems.…”

Section: Introductionmentioning

confidence: 99%

Temperature evolution, atomistic hot‐spot effects and thermal runaway during microwave heating of polyacrylonitrile: A ReaxFF molecular dynamics simulation

et al. 2021

View full text Add to dashboard Cite

Microwave is of promising applications in various chemical and material processes, however, the interactions between the microwave and the molecules from atomistic scales are lack of understanding. ReaxFF reactive molecular dynamics simulations were carried out to get insights into the interactions between the microwave and polyacrylonitrile (PAN) during microwave heating. It was found that the temperature evolution of the system was dependent on the electric field strength and frequency of the microwave. The alternate change of the electric field of the microwave leads to the alternate fluctuation of the temperature. We surprisingly predicted the atomistic hot-spot effect of microwave heating of PAN that the cyano groups were selectively heated. With an electric field intensity of 0.6 V Å -1 and a frequency of 60 GHz, the temperature of the hot-spot atoms was 300 and 500 K higher than the carbon and hydrogen atoms in the PAN backbone, respectively. We also analyzed the thermal runaway behavior of the system during microwave irradiations and found that it was attributed to the decomposition of PAN into smaller polar molecules. This work suggests that it is possible to selectively and effectively activate the cyano groups of PAN to improve their reactivity.

show abstract

Production of Low Cost Carbon-Fiber through Energy Optimization of Stabilization Process

Cited by 28 publications

References 33 publications

Artificial Neural Network and Support Vector Regression Modeling for Prediction of Mixing Time in Wet Granulation

Artificial Neural Network and Support Vector Regression Modeling for Prediction of Mixing Time in Wet Granulation

A Novel Hybrid Machine Learning Algorithm for Limited and Big Data Modeling With Application in Industry 4.0

Temperature evolution, atomistic hot‐spot effects and thermal runaway during microwave heating of polyacrylonitrile: A ReaxFF molecular dynamics simulation

Contact Info

Product

Resources

About