Machine learning predicts fretting and fatigue key mechanical properties

• Fretting crack lengths and corresponding SIF were predicted using Machine Learning • Plain fretting tests were performed on cylinder/flat configurations in partial slip • Both short and long crack arrest responses were achieved for the studied C-Mn steel • FE models were used to compute the fretting Δ K th for each crack arrest condition • Very good correlations were obtained using a neural network-based model The present work uses machine learning to predict fretting crack lengths and corresponding stress intensity factors (SIF) under partial slip conditions resulting in crack arrest. Plain fretting tests were first performed on cylinder/flat configurations in partial slip, in which the test sample was flat. Adjusting contact pressure and cylinder radius, both short and long crack arrest responses were achieved for the studied C-Mn steel. Finite element (FE) analysis was then used to compute the fretting SIF threshold Δ K th for each arrested cylinder/plane fretting crack condition. Under elastic fretting conditions, a coupled approach combining complete FE simulations modeling the crack and Rice's fracture integrals was used. When plasticity needed to be considered, an indirect method was applied, using FE simulations without the crack and classical weight functions once elastic shakedown was reached (decoupled approach). The fretting SIF threshold Δ K th could then be extrapolated to estimate the fatigue long crack SIF threshold Δ K 0 when the fretting crack was long enough. The novelty of this research work resides in the use of Machine Learning to predict the key mechanical parameters introduced above. A backpropagation algorithm with Bayesian regularization was used to identify a shallow neural network model based on just fourteen experiments. A neural network-based model was then employed to describe fretting crack lengths and corresponding SIF of the studied alloy as a function of the fretting contact radius, the maximum surface pressure, and shear traction. Perfect correlations were obtained to predict both crack depth and associated SIF threshold. An investigation was performed to determine the reliability with which samples sizes matching the count of the available experimental points can be used to predict fretting crack lengths and corresponding SIF. A Monte-Carlo bootstrapping method was used to estimate the output confidence interval corresponding to specific target inputs. This analysis provided optimistic results as relatively small datasets may be sufficient for accurate predictions. The neural network described short to long crack behaviors under elastic or elastoplastic conditions, making it a valuable tool for predicting fatigue long crack Δ K 0 based on fretting experiments.