A Bayesian regularization-backpropagation neural network model for peeling computations

TL;DR

This paper presents a Bayesian regularization-backpropagation neural network model trained on finite element data to accurately predict gecko spatula peeling forces and angles, demonstrating its effectiveness through validation.

Contribution

The study introduces a novel BR-BPNN model combined with k-fold cross validation for predicting peeling behavior based on FE simulation data.

Findings

The model accurately predicts maximum normal and tangential pull-off forces.

The neural network's optimal structure was determined through performance evaluation.

The approach shows significant potential for estimating peeling behavior.

Abstract

Bayesian regularization-backpropagation neural network (BR-BPNN) model is employed to predict some aspects of the gecko spatula peeling viz. the variation of the maximum normal and tangential pull-off forces and the resultant force angle at detachment with the peeling angle. K-fold cross validation is used to improve the effectiveness of the model. 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 shown that the BR-BPNN model in conjunction with k-fold technique has significant potential to estimate the peeling behavior.