A hierarchical mechanism-informed neural network approach for assessing fretting fatigue of dovetail joints

In the present paper, a hierarchical mechanism-informed neural network (HMNN) life prediction method was proposed. The fretting fatigue was decomposed into different fatigue problems and considered in four neural network layers, which were hierarchically and progressively established for proportional multi-axial fatigue, non-proportional multi-axial fatigue, notch fatigue and fretting fatigue, respectively. Each layer can be used to assess the fatigue life of the previous layer based on the progressive construction of fatigue complexity. The HMNN approach can predict all kinds of fatigue implemented in the method with reasonable accuracy and provides a new approach for complex fatigue assessment.

Automated summary

In this paper, a hierarchical mechanism-informed neural network (HMNN) life prediction method was proposed. Fretting fatigue was addressed in four neural network layers, each focusing on a specific type of fatigue. The HMNN approach accurately predicts various kinds of fatigue and offers a new method for assessing complex fatigue.