A Machine Learning Approach to Model Interdependencies between Dynamic Response and Crack Propagation.

Accurate damage detection in engineering structures is a critical part of structural health monitoring. A variety of non-destructive inspection methods has been employed to detect the presence and severity of the damage. In this research, machine learning (ML) algorithms are used to assess the dynamic response of the system. It can predict the damage severity, damage location, and fundamental behaviour of the system. Fatigue damage data of aluminium and ABS under coupled mechanical loads at different temperatures are used to train the model. The model shows that natural frequency and temperature appear to be the most important predictive features for aluminium. It appears to be dominated by natural frequency and tip amplitude for ABS. The results also show that the position of the crack along the specimen appears to be of little importance for either material, allowing simultaneous prediction of location and damage severity.

Investigating the Structural Dynamics and Crack Propagation Behavior under Uniform and Non-Uniform Temperature Conditions.

The robustness and stability of the system depend on structural integrity. This stability is, however, compromised by aging, wear and tear, overloads, and environmental factors. A study of vibration and fatigue cracking for structural health monitoring is one of the core research areas in recent times. In this paper, the structural dynamics and fatigue crack propagation behavior when subjected to thermal and mechanical loads were studied. It investigates the modal parameters of uncracked and various cracked specimens under uniform and non-uniform temperature conditions. The analytical model was validated by experimental and numerical approaches. The analysis was evaluated by considering different heating rates to attain the required temperatures. The heating rates were controlled by a proportional-integral-derivative (PID) temperature controller. It showed that a slow heating rate required an ample amount of time but more accurate results than quick heating. This suggested that the heating rate can cause variation in the structural response, especially at elevated temperatures. A small variation in modal parameters was also observed when the applied uniform temperatures were changed to non-uniform temperatures. This study substantiates the fatigue crack propagation behavior of pre-seeded cracks. The results show that propagated cracking depends on applied temperatures and associated mass. The appearance of double crack fronts and multiple cracks were observed. The appearance of multiple cracks seems to be due to the selection of the pre-seeded crack shape. Hence, the real cracks and pre-seeded cracks are distinct and need careful consideration in fatigue crack propagation analysis.