A reconfigurable dynamic Bayesian network for digital twin modeling of structures with multiple damage modes

Abstract

Dynamic Bayesian networks (DBNs) are commonly employed for structural digital twin modeling. At present, most researches only consider single damage mode tracking. It is not sufficient for a reusable spacecraft as various damage modes may occur during its service life. A reconfigurable DBN method is proposed in this paper. The structure of the DBN can be updated dynamically to describe the interactions between different damages. Two common damages (fatigue and bolt loosening) for a spacecraft structure are considered in a numerical example. The results show that the reconfigurable DBN can accurately predict the acceleration phenomenon of crack growth caused by bolt loosening while the DBN with time-invariant structure cannot, even with enough updates. The definition of interaction coefficients makes the reconfigurable DBN easy to track multiple damages and be extended to more complex problems. The method also has a good physical interpretability as the reconfiguration of DBN corresponds to a specific mechanism. Satisfactory predictions do not require precise knowledge of reconfiguration conditions, making the method more practical.