Modelling the Stiffness-Temperature Dependence of Resin-Rubber Blends Cured by High-Energy Electron Beam Radiation Using Global Search Genetic Algorithm

Kopal, Ivan; Vršková, Juliána; Bakošová, Alžbeta; Harničárová, Marta; Labaj, Ivan; Ondrušová, Darina; Valíček, Ján; Krmela, Ján

doi:10.3390/polym12112652

Cited by 4 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A novel, highly efficient Generalised Regression Neural Network model was developed to predict the changes in the real dynamic viscosity of the investigated rubber blends during their vulcanisation process. The raw experimental data, data prepared for visualisation, and MATLAB ® scripts enabling their detailed viewing are available at [46].…”

Section: Discussionmentioning

confidence: 99%

“…At this point, it is appropriate to note that the discrepancy between fitting error (Err max ) and prediction error (MAPE) is a direct consequence of the optimal balance between underfitting and overfitting achieved in the GRNN training process in the process of optimizing the GRNN model ( 6) by the training algorithm (12). The raw experimental data, data prepared for visualisation, and MATLAB ® scripts enabling their detailed viewing are available at [46].…”

Section: Model Generalisation Capability and Forecasting Accuracy Eva...mentioning

confidence: 99%

See 1 more Smart Citation

Intelligent Modelling of the Real Dynamic Viscosity of Rubber Blends Using Parallel Computing

Kopal,

Labaj,

Vršková

et al. 2023

Polymers

View full text Add to dashboard Cite

Modelling the flow properties of rubber blends makes it possible to predict their rheological behaviour during the processing and production of rubber-based products. As the nonlinear nature of such complex processes complicates the creation of exact analytical models, it is appropriate to use artificial intelligence tools in this modelling. The present study was implemented to develop a highly efficient artificial neural network model, optimised using a novel training algorithm with fast parallel computing to predict the results of rheological tests of rubber blends performed under different conditions. A series of 120 real dynamic viscosity–time curves, acquired by a rubber process analyser for styrene–butadiene rubber blends with varying carbon black contents vulcanised at different temperatures, were analysed using a Generalised Regression Neural Network. The model was optimised by limiting the fitting error of the training dataset to a pre-specified value of less than 1%. All repeated calculations were made via parallel computing with multiple computer cores, which significantly reduces the total computation time. An excellent agreement between the predicted and measured generalisation data was found, with an error of less than 4.7%, confirming the high generalisation performance of the newly developed model.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Model Generalisation Capability and Forecasting Accuracy Eva...mentioning

confidence: 99%

Intelligent Modelling of the Real Dynamic Viscosity of Rubber Blends Using Parallel Computing

Kopal,

Labaj,

Vršková

et al. 2023

Polymers

View full text Add to dashboard Cite

show abstract

“…The radiation curing method utilizes high energy electromagnetic radiation such as gamma-ray or X-ray [ 7 , 8 , 9 ], ultraviolet [ 10 , 11 , 12 ] or accelerated electron beams [ 9 , 13 , 14 , 15 , 16 ], and even visible light [ 17 ] for the ionization (bond breakage) of radiation-sensitive polymers since radiation curing is initiated by the ionic or free radical intermediates decomposed by the radiation sensitive resin on irradiation. On the contrary, thermal curing is by far the most popular curing method for polymer composites, with a great variety of thermal heating processes for thermal curing already in application.…”

Section: Introductionmentioning

confidence: 99%

Efficient Use of Carbon Fibers as Heating Elements for Curing of Epoxy Matrix Composites

2021

View full text Add to dashboard Cite

The aim of this study is to achieve a fully cured thermoset matrix that is heated by a direct electric current passing through the reinforcement fibers i.e., the Joule heating effect. Two types of fibers were used as heating elements for curing the epoxy resins. Kanthal resistance fibers were used as reference heating elements and subsequently, they were replaced by a Torayca Carbon Tow of the same radius. The specimens were cured by the heat produced by a direct electric current passing through the fibers and achieving temperatures of 50 °C and 70 °C. Specimens cured in a conventional oven were also manufactured, to compare the resistance heating method to the conventional one. Next, all specimens were mechanically characterized in a quasi-static three-point bending mode of loading and experimental results were compared to derive useful conclusions concerning the applicability of the technique to polymer/composite materials mass production. Finally, a preliminary economical study concerning power consumption needed for the application of both the traditional oven curing and the carbon fibers heating elements use for the manufacturing of the same amounts of materials is presented, showing a maximum financial benefit that can be achieved, on the order of 68%.

show abstract

A Generalized Regression Neural Network Model for Predicting the Curing Characteristics of Carbon Black-Filled Rubber Blends

Kopal¹,

Labaj

Vršková

et al. 2022

Polymers

View full text Add to dashboard Cite

In this study, a new generalized regression neural network model for predicting the curing characteristics of rubber blends with different contents of carbon black filler cured at various temperatures is proposed for the first time The carbon black contents in the rubber blend and cure temperature were used as input parameters, while the minimum and maximum elastic torque, scorch time, and optimal cure time, obtained from the analysis of 11 rheological cure curves registered at 10 various temperatures, were considered as output parameters of the model. A special pre-processing procedure of the experimental input and target data and the training algorithm is described. Less than 55% of the experimental data were used to significantly reduce the total number of input and target data points needed for training the model. Satisfactory agreement between the predicted and experimental data, with a maximum error in the prediction not exceeding 5%, was found. It is concluded that the generalized regression neural network is a powerful tool for intelligently modelling the curing process of rubber blends even in the case of a small dataset, and it can find a wide range of practical applications in the rubber industry.

show abstract

Modelling the Stiffness-Temperature Dependence of Resin-Rubber Blends Cured by High-Energy Electron Beam Radiation Using Global Search Genetic Algorithm

Cited by 4 publications

References 36 publications

Intelligent Modelling of the Real Dynamic Viscosity of Rubber Blends Using Parallel Computing

Intelligent Modelling of the Real Dynamic Viscosity of Rubber Blends Using Parallel Computing

Efficient Use of Carbon Fibers as Heating Elements for Curing of Epoxy Matrix Composites

A Generalized Regression Neural Network Model for Predicting the Curing Characteristics of Carbon Black-Filled Rubber Blends

Contact Info

Product

Resources

About