A data-mechanism driven method for progressive analysis of fatigue damage in composites

Abstract

With the wide application of fibre-reinforced composites in aerospace, the fatigue problem of composites is becoming more prominent. In order to achieve efficient and accurate fatigue damage analysis, a data-mechanism driven method for the progressive analysis of fatigue damage in composites is proposed, in which a single-hiddenlayer neural network as its fatigue constitutive law for simulations of fatigue delamination under cyclic loading. The Paris-law-informed regulation is used to achieve data-mechanism fusion for neural network model training. The ability to analyze fatigue delamination is validated in the full range of mode-Ⅰ and mode-Ⅱ as well as mixed modes of different mode ratios using double cantilever beam (DCB) and 4-point end flexure (4ENF). The applicability of the cohesive model in the case of complex fatigue delamination front is verified by using the reinforced double cantilever beam (R-DCB) model. The results show that the data-mechanism driven fatigue damage progressive analysis method for composites could rapidly and effectively simulate the composite delamination propagation with high fidelity, which can provide a new idea and method for composite structure design and safety assurance.

Keywords

• cohesive model
• neural network
• composites
• fatigue
• finite element