Predicting kerf quality characteristics in laser cutting of basalt fibers reinforced polymer composites using neural network and chimp optimization

Najjar, I.M.R.; Sadoun, A.M.; Elaziz, Mohamed Abd; Abdallah, Ahmed M.; Fathy, Ahmed; Elsheikh, Ammar H.

doi:10.1016/j.aej.2022.04.032

Cited by 83 publications

(22 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1-15, obtained through chemical component content testing, were taken as comparative sequences 1, 2, and 3, respectively, and Young's modulus as reference sequence X 0 (m) (k), and the grey model of the chemical components and the mechanical properties of WPF was established. The grey differential equation of GM (1,4) was shown in Equation ( 2) [31].…”

Section: Parameter Definition Of Gm Establishmentmentioning

confidence: 99%

“…The Matlab programming software (MathWorks. Inc., Natick, MA, USA) was utilized to calculate the Equation ( 6) to obtain a and b i , and then the influence of the content of each chemical component on the mechanical property could be judged through the grey differential equation of GM (1,4).…”

Section: Parameter Definition Of Gm Establishmentmentioning

confidence: 99%

“…In addition, a and b i of Equation (7) were obtained according to Equation ( 6) and substituted into Equation (2). Then the GM (1,4) model was established to explore the influence rule of chemical component contents of WPF on the Young's modulus.…”

Section: Establishment Of Gm and Error Analysismentioning

confidence: 99%

“…With further studies on WPF, its application in the textile field has broad prospects, such as its use in textiles as an elastic composite material [1,2]. The mechanical properties of WPF have a great influence on the performance of textiles, which in turn is affected by the content of chemical components [3,4]. According to previous studies, there are certain Materials 2022, 15, 4989 2 of 11 differences in the chemical component content of fibers extracted from various parts of the WPF (Table 1) [5][6][7].…”

Section: Introductionmentioning

confidence: 99%

“…The main purpose of this work is to develop a grey model for the rapid determination of mechanical properties based on the chemical components of WPF. Firstly, the NIR model was established to predict the content of each component quickly, and then the GM (1,4) model was established to realize the efficient prediction of the Young's modulus of WPF. The rapid selection of fibers for spinning has promoted the industrialized production of WPF, which is conducive to the accelerated development of the transformation and upgrading of these enterprises.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Rapid Prediction of Mechanical Properties Based on the Chemical Components of Windmill Palm Fiber

et al. 2022

View full text Add to dashboard Cite

During spinning, the chemical component content of natural fibers has a great influence on the mechanical properties. How to rapidly and accurately measure these properties has become the focus of the industry. In this work, a grey model (GM) for rapid and accurate prediction of the mechanical properties of windmill palm fiber (WPF) was established to explore the effect of chemical component content on the Young’s modulus. The chemical component content of cellulose, hemicellulose, and lignin in WPF was studied using near-infrared (NIR) spectroscopy, and an NIR prediction model was established, with the measured chemical values as the control. The value of RC and RCV were more than 0.9, while the values of RMSEC and RMSEP were less than 1, which reflected the excellent accuracy of the NIR model. External validation and a two-tailed t-test were used to evaluate the accuracy of the NIR model prediction results. The GM(1,4) model of WPF chemical components and the Young’s modulus was established. The model indicated that the increase in cellulose and lignin content could promote the increase in the Young’s modulus, while the increase in hemicellulose content inhibited it. The establishment of the two models provides a theoretical basis for evaluating whether WPF can be used in spinning, which is convenient for the selection of spinning fibers in practical application.

show abstract

Section: Parameter Definition Of Gm Establishmentmentioning

confidence: 99%

Section: Parameter Definition Of Gm Establishmentmentioning

confidence: 99%

Section: Establishment Of Gm and Error Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Rapid Prediction of Mechanical Properties Based on the Chemical Components of Windmill Palm Fiber

et al. 2022

View full text Add to dashboard Cite

show abstract

Virtual Analyzers for MI and Density Based on Neural Networks Improved through an Integrated Strategy Involving a Constructive Algorithm and Definition of Initial Weights

Silva

Fontes

Embiruçu

2023

Macro Reaction Engineering

View full text Add to dashboard Cite

This work presents the development and validation of two virtual analyzers (density and Melt Index (MI)) for quality monitoring and control of the final product in an industrial unit of Linear Polyethylene (LPE). Both models are based on Feedforward Neural Networks which are improved through a strategy involving the initial estimation of weights and a constructive algorithm to define the number of hidden units. The initialization strategy is based on linearization of the neural model with only one hidden unit (nonlinear model) and subsequent optimization of this model by maximizing its similarity to the standard linear regression model whose solution is obtained analytically. The Initial Neural Model (INM) is then used as a starting point for a gradual increase in the number of hidden units. In a validation test involving MI and density values collected over 2 years of operation, the neural model is able to predict these properties with mean percentage errors equal to 0.81% (MI) and 0.04% (density) and determination coefficients equal to 0.970 (MI) and 0.983 (density). The population coefficient estimated in all tests involving grade transitions (0.96) shows a strong linear correlation between the proposed model and laboratory measurements.

show abstract

Effect of nano‐silica on fatigue behavior of glass fiber‐reinforced epoxy composite laminates: A Weibull distribution approach

Gupta,

Singh,

Saini

2023

Polymer Composites

View full text Add to dashboard Cite

The aim of this study is to assess the impact of nano‐silica in glass fiber‐reinforced epoxy composite (GFEC) subjected to static and fatigue loading. Laminates were prepared in compression molding machine followed by the tensile test and tension‐tension fatigue testing at five different stress levels (from 50% to 90% of ultimate tensile strength). The addition of 3 wt% of nano‐silica with epoxy improved the tensile and fatigue strength as compared to neat GFEC. Scanning electron microscope (SEM) images of the fractured specimen showed the damage pattern which indicates that neat GFEC laminate exhibited damage patterns characterized by fiber breakage and matrix cracking. On the other hand, the modified GFEC with nano‐silica showed damage patterns including fiber pullout accompanied by fiber breakage and matrix cracking. During cyclic loading, the stress–strain hysteresis loop shows a reduced slope, indicating a decrease in the dynamic modulus of the specimen. This reduction in slope signifies a loss of stiffness during cyclic loading, particularly at high‐stress levels. The highest dynamic modulus at high‐stress levels indicates a rapid progression of severe damage and a shorter fatigue life. On the other hand, at low‐stress levels, the lower magnitude of dynamic modulus suggests a moderate damage progression and a longer fatigue life.Highlights Effect of nano‐silica in GFEC under static and fatigue loading conditions. GFEC with 3 wt% of nano‐silica shows improved tensile and fatigue strength. Examination of damage patterns through SEM analysis of the fractured surface. Depiction of the failure modes using damage pattern under fatigue loading. Comparison of fatigue life and dynamic modulus for neat and modified GFEC.

show abstract

Predicting kerf quality characteristics in laser cutting of basalt fibers reinforced polymer composites using neural network and chimp optimization

Cited by 83 publications

References 57 publications

Rapid Prediction of Mechanical Properties Based on the Chemical Components of Windmill Palm Fiber

Rapid Prediction of Mechanical Properties Based on the Chemical Components of Windmill Palm Fiber

Virtual Analyzers for MI and Density Based on Neural Networks Improved through an Integrated Strategy Involving a Constructive Algorithm and Definition of Initial Weights

Effect of nano‐silica on fatigue behavior of glass fiber‐reinforced epoxy composite laminates: A Weibull distribution approach

Contact Info

Product

Resources

About