A Bayesian regularization-backpropagation neural network model for peeling computations
This is an incremental application of an existing neural network method to a specific biomechanics problem, aimed at researchers in materials science or bio-inspired adhesion.
The paper tackled predicting gecko spatula peeling forces and angles using a Bayesian regularization-backpropagation neural network (BR-BPNN) model with k-fold cross-validation, showing it has significant potential to estimate peeling behavior with relative error comparisons to finite element results.
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.