A Bayesian regularization-backpropagation neural network model for peeling computations

Bayesian regularization-backpropagation neural network (BR-BPNN), a machine learning algorithm, is employed to predict some aspects of the gecko spatula peeling such as the variation of the maximum normal and tangential pull-off forces and the resultant force angle at detachment with the peeling angle. The input data is taken from finite element (FE) peeling results. The neural network is trained with 75% of the FE dataset. The remaining 25% are utilized to predict the peeling behavior. The training performance is evaluated for every change in the number of hidden layer neurons to determine the optimal network structure. The relative error is calculated to draw a clear comparison between predicted and FE results. It is observed that BR-BPNN models have significant potential to estimate the peeling behavior.

[1]  Kaijun Yang,et al.  Prediction of CH4 adsorption on different activated carbons by developing an optimal multilayer perceptron artificial neural network , 2019, Energy Sources, Part A: Recovery, Utilization, and Environmental Effects.

[2]  Jin H. Huang,et al.  Detection of cracks using neural networks and computational mechanics , 2002 .

[3]  Shaohua Chen,et al.  Effect of thin-film length on the peeling behavior of film-substrate interfaces. , 2019, Physical review. E.

[4]  David J. C. MacKay,et al.  A Practical Bayesian Framework for Backpropagation Networks , 1992, Neural Computation.

[5]  Suh-Yin Lee,et al.  Mining frequent itemsets over data streams using efficient window sliding techniques , 2009, Expert Syst. Appl..

[6]  Roger A. Sauer,et al.  A contact mechanics model for quasi‐continua , 2007 .

[7]  David Labonte,et al.  Biomechanics of shear-sensitive adhesion in climbing animals: peeling, pre-tension and sliding-induced changes in interface strength , 2015, bioRxiv.

[8]  David Labonte,et al.  Dynamic biological adhesion: mechanisms for controlling attachment during locomotion , 2019, Philosophical Transactions of the Royal Society B.

[9]  N. Huber,et al.  A neural network tool for identifying the material parameters of a finite deformation viscoplasticity model with static recovery , 2001 .

[10]  Kyriakos Komvopoulos,et al.  Adhesion and friction forces in microelectromechanical systems: mechanisms, measurement, surface modification techniques, and adhesion theory , 2003 .

[11]  Roger A Sauer,et al.  Multiscale modelling and simulation of the deformation and adhesion of a single gecko seta , 2009, Computer methods in biomechanics and biomedical engineering.

[12]  Peter Sergeant,et al.  Comparison of analytical, finite element and neural network methods to study magnetic shielding , 2010, Simul. Model. Pract. Theory.

[13]  M. K. Soni,et al.  Artificial neural network based peak load forecasting using Levenberg-Marquardt and quasi-Newton methods , 2002 .

[14]  R S Fearing,et al.  High friction from a stiff polymer using microfiber arrays. , 2006, Physical review letters.

[15]  Xiangjun Zhang,et al.  Controllable and switchable capillary adhesion mechanism for bio-adhesive pads: Effect of micro patterns , 2009 .

[16]  Genki Yagawa,et al.  Computational mechanics enhanced by deep learning , 2017 .

[17]  Genki Yagawa,et al.  NEW REGULARIZATION BY TRANSFORMATION FOR NEURAL NETWORK BASED INVERSE ANALYSES AND ITS APPLICATION TO STRUCTURE IDENTIFICATION , 1996 .

[18]  M. Sitti,et al.  Bioinspired Composite Microfibers for Skin Adhesion and Signal Amplification of Wearable Sensors , 2017, Advanced materials.

[19]  Roger A. Sauer,et al.  A COMPOSITE TIME INTEGRATION SCHEME FOR DYNAMIC ADHESION AND ITS APPLICATION TO GECKO SPATULA PEELING , 2014 .

[20]  Markus J. Buehler,et al.  Bioinspired hierarchical composite design using machine learning: simulation, additive manufacturing, and experiment , 2018 .

[21]  M. Cutkosky,et al.  Frictional adhesion: a new angle on gecko attachment , 2006, Journal of Experimental Biology.

[22]  K. Autumn,et al.  Mechanisms of Adhesion in Geckos1 , 2002, Integrative and comparative biology.

[23]  Tomonari Furukawa,et al.  Neural network constitutive modelling for non‐linear characterization of anisotropic materials , 2011 .

[24]  C. Zhu,et al.  Kinetics and mechanics of cell adhesion. , 2000, Journal of biomechanics.

[25]  Shigeki Saito,et al.  Geckos' foot hair structure and their ability to hang from rough surfaces and move quickly , 2006 .

[26]  Jacek M. Zurada,et al.  Introduction to artificial neural systems , 1992 .

[27]  Austin M. Garner,et al.  Geckos go the Distance: Water's Effect on the Speed of Adhesive Locomotion in Geckos , 2017, Journal of Herpetology.

[28]  Naif Alajlan,et al.  A novel deep learning based method for the computational material design of flexoelectric nanostructures with topology optimization , 2019, Finite Elements in Analysis and Design.

[29]  Hosseini Sadegh,et al.  Classification of acoustic emission signals generated from journal bearing at different lubrication conditions based on wavelet analysis in combination with artificial neural network and genetic algorithm , 2016 .

[30]  T. Troczynski,et al.  Peel adhesion test for thermal spray coatings , 1994 .

[31]  Shinobu Yoshimura,et al.  A New Local Contact Search Method Using a Multi-Layer Neural Network , 2007 .

[32]  Dimitrios I. Fotiadis,et al.  Artificial neural networks for solving ordinary and partial differential equations , 1997, IEEE Trans. Neural Networks.

[33]  Pavel Neuzil,et al.  The nature of the gecko lizard adhesive force. , 2005, Biophysical journal.

[34]  Klaus Friedrich,et al.  Artificial neural networks for predicting sliding friction and wear properties of polyphenylene sulfide composites , 2011 .

[35]  Martin T. Hagan,et al.  Gauss-Newton approximation to Bayesian learning , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[36]  J. J. Kauzlarich,et al.  The influence of peel angle on the mechanics of peeling flexible adherends with arbitrary load–extension characteristics , 2005 .

[37]  R. Full,et al.  Adhesive force of a single gecko foot-hair , 2000, Nature.

[38]  Robert M. McMeeking,et al.  Detachment of compliant films adhered to stiff substrates via van der Waals interactions: role of frictional sliding during peeling , 2014, Journal of The Royal Society Interface.

[39]  Roger A. Sauer,et al.  The Peeling Behavior of Thin Films with Finite Bending Stiffness and the Implications on Gecko Adhesion , 2011 .

[40]  Goutam Saha,et al.  Lung sound classification using cepstral-based statistical features , 2016, Comput. Biol. Medicine.

[41]  Ronald S. Fearing,et al.  Towards friction and adhesion from high modulus microfiber arrays , 2007 .

[42]  Zhenhai Xia,et al.  Dynamic self-cleaning in gecko setae via digital hyperextension , 2012, Journal of The Royal Society Interface.

[43]  Bin Chen,et al.  Pre-tension generates strongly reversible adhesion of a spatula pad on substrate , 2009, Journal of The Royal Society Interface.

[44]  Kristofer G. Reyes,et al.  Prediction of Nanoscale Friction for Two-Dimensional Materials Using a Machine Learning Approach , 2020, Tribology Letters.

[45]  Stanislav N. Gorb,et al.  The effect of surface roughness on the adhesion of elastic plates with application to biological systems , 2003 .

[46]  H. Abdul Razak,et al.  Structural damage detection of steel bridge girder using artificial neural networks and finite element models , 2013 .

[47]  M. Lefik,et al.  Artificial neural network as an incremental non-linear constitutive model for a finite element code , 2003 .

[48]  Roger A. Sauer,et al.  A geometrically exact finite beam element formulation for thin film adhesion and debonding , 2014 .

[49]  S. Islam,et al.  Machine Learning Enabled Wearable Brain Deformation Sensing System , 2019, 2019 IEEE Signal Processing in Medicine and Biology Symposium (SPMB).

[50]  Wei Sun,et al.  A deep learning approach to estimate stress distribution: a fast and accurate surrogate of finite-element analysis , 2018, Journal of The Royal Society Interface.

[51]  Dave Winkler,et al.  Bayesian Regularization of Neural Networks , 2009, Artificial Neural Networks.

[52]  Y. W. Zhang,et al.  Sliding-induced non-uniform pre-tension governs robust and reversible adhesion: a revisit of adhesion mechanisms of geckos , 2012, Journal of The Royal Society Interface.

[53]  David Nowell,et al.  A machine learning approach to the prediction of fretting fatigue life , 2020, Tribology International.

[54]  Zhilong Peng,et al.  Effect of pre-tension on the peeling behavior of a bio-inspired nano-film and a hierarchical adhesive structure , 2012 .

[55]  Huajian Gao,et al.  Mechanics of hierarchical adhesion structures of geckos , 2005 .

[56]  Roger A. Sauer,et al.  Enriched contact finite elements for stable peeling computations , 2011 .

[57]  R. Sauer,et al.  An energy‐momentum‐conserving temporal discretization scheme for adhesive contact problems , 2013 .

[58]  Murat Kayri,et al.  Predictive Abilities of Bayesian Regularization and Levenberg–Marquardt Algorithms in Artificial Neural Networks: A Comparative Empirical Study on Social Data , 2016 .

[59]  Jonathan L. Ticknor.  A Bayesian regularized artificial neural network for stock market forecasting , 2013, Expert Syst. Appl..

[60]  Yu Tian,et al.  Adhesion and friction in gecko toe attachment and detachment , 2006, Proceedings of the National Academy of Sciences.

[61]  Saipraneeth Gouravaraju,et al.  Investigating the normal and tangential peeling behaviour of gecko spatulae using a coupled adhesion-friction model , 2019, The Journal of Adhesion.

[62]  Roger A. Sauer,et al.  A Survey of Computational Models for Adhesion , 2016 .

[63]  R. D. Wood,et al.  Nonlinear Continuum Mechanics for Finite Element Analysis , 1997 .

[64]  Ivan Argatov,et al.  An artificial neural network supported regression model for wear rate , 2019, Tribology International.

[65]  Antonio Delgado,et al.  Damage detection on crates of beverages by artificial neural networks trained with finite-element data , 2004 .

[66]  Genki Yagawa,et al.  Implicit constitutive modelling for viscoplasticity using neural networks , 1998 .

[67]  Peter Wriggers,et al.  Formulation and analysis of a three-dimensional finite element implementation for adhesive contact at the nanoscale , 2009 .

[68]  Saipraneeth Gouravaraju,et al.  On the presence of a critical detachment angle in gecko spatula peeling - a numerical investigation using an adhesive friction model , 2020, The Journal of Adhesion.

[69]  Ai Kah Soh,et al.  Peeling behavior of a bio-inspired nano-film on a substrate , 2010 .

[70]  E. Oñate,et al.  Neural networks for variational problems in engineering , 2008 .

[71]  Roger A. Sauer,et al.  A detailed 3D finite element analysis of the peeling behaviour of a gecko spatula , 2013, Computer methods in biomechanics and biomedical engineering.

[72]  Genki Yagawa,et al.  Neural networks in computational mechanics , 1996 .

[73]  Genki Yagawa,et al.  A surface-to-surface contact search method enhanced by deep learning , 2020, Computational Mechanics.

[74]  Grace X. Gu,et al.  Designing adhesive pillar shape with deep learning-based optimization. , 2020, ACS applied materials & interfaces.

[75]  Ralph Spolenak,et al.  Resolving the nanoscale adhesion of individual gecko spatulae by atomic force microscopy , 2005, Biology Letters.

[76]  Martin T. Hagan,et al.  Neural network design , 1995 .

[77]  Roger A. Sauer,et al.  Continuum contact models for coupled adhesion and friction , 2018, The Journal of Adhesion.

[78]  Dan Givoli,et al.  Finite–Element Mesh Generation Using Self–Organizing Neural Networks , 1997 .

[79]  Robert M. McMeeking,et al.  Peeling of a tape with large deformations and frictional sliding , 2013 .

[80]  Samanthe M. Lyons,et al.  Measuring systematic changes in invasive cancer cell shape using Zernike moments. , 2016, Integrative biology : quantitative biosciences from nano to macro.

[81]  Ridha Hambli,et al.  Numerical procedure for multiscale bone adaptation prediction based on neural networks and finite element simulation , 2011 .

[82]  Yu Tian,et al.  Peel-Zone Model of Tape Peeling Based on the Gecko Adhesive System , 2007 .

[83]  S. Gautam,et al.  NURBS-based isogeometric analysis for stable and accurate peeling computations , 2021 .