Abstract
The mechanical properties of hydrogen functionalized graphene (HFG) sheets werepredicted in this work by using artificial neural network approach. Thepredictions of tensile strength of HFG sheets made by the proposed approach arecompared to those generated by molecular dynamics simulations. The resultsindicate that our proposed computing technique can be used as a powerful toolfor predicting the tensile strength of the HFG sheet.
Similar content being viewed by others
Avoid common mistakes on your manuscript.
Background
Research in graphene has attracted significant interest in recent years due to itsremarkable mechanical [1] and physical properties [2, 3]. A single-layer graphene sheet has the thickness of only one carbon atomwhich makes it the thinnest material [4] with a large specific surface area [5]. This feature of graphene makes it an ideal candidate fornanoelectromechanical systems (NEMS) [6] and nanofluidic devices. These future applications require a criticalunderstanding of the exceptional mechanical properties of graphene for itsapplication in NEMS and nanolevel biological devices. Theoretical studies ongraphene are a popular mode of research, employing ab initio calculationsor molecular dynamics (MD) simulation technique.
Application of soft computing methods such as artificial neural networks (ANN),genetic programming, and fuzzy logic can be used as an alternative method formodeling complex behavior of materials such as graphene. These methods require inputtraining data which can be obtained from the analytical tools such as MD that isbased on a specific geometry and temperature. Based on the input, the proposedcomputing method can then be able to generate meaningful solutions for complicatedproblems [7–11]. Additionally, among the various soft computing methods described above,ANN offers the advantage of a fast and cost-effective formulation of a mathematicalmodel based on multiple variables with no existing analytical models [12, 13]. It is to the best of author's knowledge that limited or no work existson the application of soft computing models on the tensile properties of graphenesheets.
Hence, in the present work, we have proposed ANN method to model the elasticcharacteristics of hydrogen functionalized graphene (HFG). The values of tensilestrength of HFG generated by MD simulations are further fed into the paradigm ofANN.
Nanoscale material modeling by MD simulation
The classical MD method is deployed to carry out the numerical simulation. Inthis capacity, Newton's equations of motion are computed by means of Brenner'ssecond-generation bond order (REBO) function [14] for the set of atoms which are covalently bonded. The REBO potentialis able to accurately describe the properties of solid-state and molecularcarbon nanostructures [15, 16] while maintaining the accuracies of the ab initio andsemi-empirical methods in simulating large systems [15–21]. The mathematical form of the potential equations is defined as
where VR(r ij ) and VA(r ij ) are the repulsive and attractive pair terms and b ij term is used to include the reactive empirical bond order between theatoms.
The MD simulation procedure described here is similar to our previous work as canbe seen in [15]. The tensile loading procedure of HFG sheet is shown inFigure 1. As an illustration, the morphologicalcharacteristics of the HFG sheet of length 100 Å under tension isdepicted in Figure 2. The data hence generated by ourMD simulation agrees very well with the literature [15, 20], and hence, we can validate the reliability of our MD simulation.
Methods
The data obtained by the MD simulation are shown in Tables 1 and 2 which represent the data for trainingand testing samples, respectively. The main inputs considered in our study arethe percentage of hydrogen functionalization and simulation temperature. Theoutput of our study is the tensile strength of HFG. In order to explicitly testthe extrapolation capability of method, 20 samples are used for training and 11are used for testing. Training samples consist of values of tensile strength attemperatures of 0 and 300 K, whereas testing samples consist of values oftemperature at 600 K.
Nanoscale material modeling by ANN approach
In this paper, we proposed ANN approach. In this approach, data obtained from MDis fed into the paradigm of ANN for training of network. ANN network consist ofthree layers: input, hidden, and output layers. Input layer consist of twoneurons since there are two inputs [22–31]. The number of neurons in the hidden layer is chosen based ontrial-and-error method. The output layer comprise of single neuron, i.e., outputof the system. The neurons of one layer to the neurons of pre-and-after layerare connected through weighted links.
Weights are initialized and are multiplied by input values specified by eachneuron. The neuron estimate summation of weighted inputs and passes it to thetransfer function (A) which produces an output Y p .
where w i is weight, x i is the i th input variable, and δ is the thresholdor offset of the neuron. The activation function used is sigmoid logisticfunction given by
The difference between the output value of network and actual value for a samplei is given by
where Ac i and M i are actual and predicted values for i th sample, respectively,and M is the number of neurons in the output of network. The averageerror for the whole network is given by
where N is the total number of samples. The Levenberg-Marquardtalgorithm [32] that works on the principle of the second derivative is used tooptimize the Error p . The simpler form of Hessian matrix is used and the algorithm iteratesweights using formulae
where j is the Jacobian matrix that consists of the first derivatives ofthe network errors, e is a vector of network errors, μ isthe learning rate, and I is the identity matrix. The weights areupdated by LMA until the threshold error is achieved. The computation of weightsis iterative and it consumes time.
In the present work, feed-forward network of three layers is implemented inMATLAB R2010b. The number of neurons in hidden layer is determined based on theminimum value of root-mean-square error (RMSE) of the model on the training dataset. A trial-and-error approach is adopted to select the number of neurons inthe hidden layers. It was found that for number of neurons six, the RMSE isminimum, and therefore, the ANN model with single hidden layer of six neurons isselected. The performance of the selected ANN model is discussed in the‘Performance comparison of proposed approach’ section.
Results and discussion
The predictions obtained from the proposed approach is compared to thosegenerated using MD simulations based on square of correlation coefficient(R2) given by
where M i and A i are predicted and actual values, respectively, and are the average values of predicted and actual, respectively,and n is number of training samples.
The results obtained from the simulation studies and predicted by using proposedapproach on training and testing data is shown in Figures 3 and 4, respectively. The graph shown inFigure 3 indicates that the proposed approach hasimpressively well learned the non-linear relationship between the input andoutput process parameters with high correlation values. The result of testingphase shown in Figure 4 indicates that the valuespredicted by MD-ANN approach are well in agreement with the simulatedvalues.
Conclusion
The performance of the proposed MD-ANN approach is evaluated in the‘Performance comparison of proposed approach’ section. The resultsconclude that the MD-ANN model have shown excellent generalization ability withhigh statistical values of R2 on testing data. The high generalization ability of the MD-ANNmodel is beneficial for MD experts who are currently looking for high fidelitymodels that predict the tensile strength of graphene under uncertain inputprocess conditions, and therefore, the cost of having to run additional MDsimulations can be avoided. The model can be used offline for prediction and canbe further optimized to determine the optimum input process parameters thatmaximize the tensile strength of nanomaterials.
References
Lee C, Wei X, Kysar JW, Hone J: Measurement of the elastic properties and intrinsic strength of monolayergraphene. Science 2008,321(5887):385–388. 10.1126/science.1157996
Balandin AA, Ghosh S, Bao WZ, Calizo I, Teweldebrhan D, Miao F, Lau CN: Superior thermal conductivity of single-layer graphene. Nano Lett 2008,8(3):902–907. 10.1021/nl0731872
Williams JR, DiCarlo L, Marcus CM: Quantum hall effect in a gate-controlled p-n junction of graphene. Science 2007,317(5838):638–641. 10.1126/science.1144657
Novoselov KS, Geim AK, Morozov SV, Jiang D, Zhang Y, Dubonos SV, Grigorieva IV, Firsov AA: Electric field effect in atomically thin carbon films. Science 2004,306(5696):666–669. 10.1126/science.1102896
Geim AK: Graphene: status and prospects. Science 2009,324(5934):1530–1534. 10.1126/science.1158877
Standley B, Bao WZ, Zhang H, Bruck J, Lau CN, Bockrath M: Graphene-based atomic-scale switches. Nano Lett 2008,8(10):3345–3349. 10.1021/nl801774a
Kordon A, Castillo F, Smits G, Kotanchek M: Application issues of genetic programming in industry. Gen Prog Theory Prac III 2006, 9: 241–258. 10.1007/0-387-28111-8_16
Reihanian M, Asadullahpour SR, Hajarpour S, Gheisari KH: Application of neural network and genetic algorithm to powder metallurgy ofpure iron. Mat Design 2011,32(6):3183–3188. 10.1016/j.matdes.2011.02.049
Ramanan TR, Sridharan R, Shashikant KS, Haq AN: An artificial neural network based heuristic for flow shop schedulingproblems. J Intell Manufactur 2011,22(2):279–288. 10.1007/s10845-009-0287-5
Liao KW, Fan JC, Huang CL: An artificial neural network for groutability prediction of permeationgrouting with microfine cement grouts. Comp Geotechnics 2011,38(8):978–986. 10.1016/j.compgeo.2011.07.008
Garg A, Tai K: Comparison of statistical and machine learning methods in modelling of datawith multicollinearity. Int J Modell Identification Control 2013,18(4):295–312. 10.1504/IJMIC.2013.053535
Garcia-Mateo C, Capdevila C, Caballero FG, de Andres CG: Artificial neural network modeling for the prediction of criticaltransformation temperatures in steels. J Mater Sci 2007,42(14):5391–5397. 10.1007/s10853-006-0881-2
Garg A, Tai K, Lee CH, Savalani MM: A hybrid M5’-genetic programming approach for ensuring greatertrustworthiness of prediction ability in modelling of FDM process. J Intell Manufactur doi: 10.1007/s10845–013–0734–1 doi: 10.1007/s10845-013-0734-1
Brenner DW, Shenderova OA, Harrison JA, Stuart SJ, Ni B, Sinnott SB: A second-generation reactive empirical bond order (REBO) potential energyexpression for hydrocarbons. J Physics-Condensed Matter 2002,14(4):783–802. 10.1088/0953-8984/14/4/312
Wong CH, Vijayaraghavan V: Nanomechanics of free form and water submerged single layer graphene sheetunder axial tension by using molecular dynamics simulation. Mater Sci Engineer A 2012, 556: 420–428.
Wong CH, Vijayaraghavan V: Nanomechanics of imperfectly straight single walled carbon nanotubes underaxial compression by using molecular dynamics simulation. Comp Mater Sci 2012,53(1):268–277. 10.1016/j.commatsci.2011.08.011
Vijayaraghavan V, Wong CH: Nanomechanics of single walled carbon nanotube with water interactions underaxial tension by using molecular dynamics simulation. Comp Mater Sci 2013, 79: 519.
Vijayaraghavan V, Wong CH: Shear deformation characteristics of single walled carbon nanotube with waterinteractions by using molecular dynamics simulation. Physica E Low-Dimensional Sys Nanostructures doi:/10.1016/j.physe.2013.06.025 doi:/10.1016/j.physe.2013.06.025
Vijayaraghavan V, Wong CH: Temperature, defect and size effect on the elastic properties of imperfectlystraight carbon nanotubes by using molecular dynamics simulation. Comp Mater Sci 2013, 71: 184–191.
Vijayaraghavan V, Wong CH: Tensile loading characteristics of free-form and water submerged single layergraphene sheet. Proc 12th IEEE Confer Nanotechnol 2012. doi: 10.1109/NANO.2012.6321916 doi: 10.1109/NANO.2012.6321916
Wong CH, Vijayaraghavan V: Nanomechanics of nonideal single- and double-walled carbon nanotubes. J Nanomaterials doi: 10.1155/2012/490872 doi: 10.1155/2012/490872
Garg A, Rachmawati L, Tai K: Classification-driven model selection approach of genetic programming inmodelling of turning process. Int J Advanced Manufactur Technol doi: 10.1007/s00170–013–5103-x doi: 10.1007/s00170-013-5103-x
Garg A, Savalani MM, Tai K: State-of-the-Art in empirical modeling of rapid prototyping processes. Rapid Prototyping J in press in press
Garg A, Tai K: A hybrid genetic programming–artificial neural network approach formodeling of vibratory finishing process. Int Proc Comp Sci Info Technol (IPCSIT) 2011, 18: 14–19.
Garg A, Tai K: Comparison of regression analysis, artificial neural network and geneticprogramming in handling the multicollinearity problem, pp.353–358. Wuhan, China: Proceedings of 2012 International Conference on Modelling,Identification and Control (ICMIC 2012); 2012.
Benyelloul K, Aourag H, Elastic constants of austenitic stainless steel: Investigation by the first-principles calculations and the artificial neuralnetwork approach.. Comp Mater Sci 67; 2013:353–358.
Garg A, Sriram S, Tai K: Empirical Analysis of Model Selection Criteria for Genetic Programming inModeling of Time Series System, pp. 84–88. Singapore: Proceedings of 2013 IEEE Conference on ComputationalIntelligence for Financial Engineering & Economics (CIFEr); 2013.
Garg A, Tai K: Selection of a Robust Experimental Design for the Effective Modeling ofNonlinear Systems using Genetic Programming, pp. 293–298. Singapore: Proceedings of 2013 IEEE Symposium Series on ComputationalIntelligence and Data mining (CIDM); 2013.
Garg A, Bhalerao Y, Tai K: Review of empirical modeling techniques for modeling of turning process. Int J Modell Identification Control 2013,20(2):121–129. 10.1504/IJMIC.2013.056184
Esmailzadeh M, Aghaie-Khafri M: Finite element and artificial neural network analysis of ECAP. Comp Mater Sci 63; 2012:127–133.
Garg A, Vijayaraghavan V, Mahapatra SS, Tai K, Wong CH: Performance evaluation of microbial fuel cell by artificial intelligencemethods. Expert systems with applications 2013. doi: 10.1016/j.eswa.2013.08.038 doi: 10.1016/j.eswa.2013.08.038
Cherkassky V, Ma Y: Comparison of model selection for regression. Neural Comput 2003,15(7):1691–1714. 10.1162/089976603321891864
Acknowledgements
VV and AG gratefully acknowledge the financial support in form of scholarshipprovided by the School of Mechanical and Aerospace Engineering, NanyangTechnological University, Singapore.
Author information
Authors and Affiliations
Corresponding author
Additional information
Competing interests
The authors declare that they have no competing interests.
Authors' contributions
VV carried out preliminary simulations to confirm that data generated confirm toliterature and is supervised by CHW. AG carried out the computational simulationsdesigned and formulated by YB and is supervised by KT. All authors read and approvedthe final manuscript.
Authors’ original submitted files for images
Below are the links to the authors’ original submitted files for images.
Rights and permissions
Open Access This article is distributed under the terms of the Creative Commons Attribution 2.0 International License (https://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
About this article
Cite this article
Vijayaraghavan, V., Garg, A., Wong, C.H. et al. Predicting the mechanical characteristics of hydrogen functionalized graphene sheets using artificial neural network approach. J Nanostruct Chem 3, 83 (2013). https://doi.org/10.1186/2193-8865-3-83
Received:
Accepted:
Published:
DOI: https://doi.org/10.1186/2193-8865-3-83