The fatigue life model and fatigue stiffness degradation model are most crucial components in establishment of fatigue progressive damage model (FPDM). Based on numerous static and fatigue experiments of glass fiber reinforced polymer-matrix composites (GFRP) 3232A/Glass, a novel normalized FPDM for complete stress level based on artificial neural network (ANN) has been built: (1) By analyzing fatigue experimental data, the construction method of fatigue life model is deeply investigated. Furthermore, a normalized fatigue life model (NFLM) predicting fatigue life considering simultaneously tension–tension (T-T) fatigue and compression-compression (C–C) fatigue is developed, which has been validated by experimental data. It is expected to reduce experimental time and costs by nearly half; (2) To fully consider the influence of stress level and remove the constraint of the shape of stiffness degradation function, the traditional models are no longer suitable. Thus, a fatigue stiffness degradation model based on ANN (FSDM-ANN) has been constructed, which overcomes drawbacks of the traditional models. The results predicted by FSDM-ANN are consistent with fatigue data in different stress levels; (3) Due to distortion of the fatigue life prediction of extreme high-cycle and low-cycle, an empirical data extrapolation method is proposed here to construct a modified FSDM-ANN, which greatly improves prediction accuracy of stiffness degradation for complete stress levels.
Read full abstract