Structural damage detection based on cloud model and Dempster-Shafer evidence theory

Abstract

Cloud model and D-S theory have been widely used in uncertainty reasoning. Meanwhile, modal strain energy and Inner Product Vector are also utilized as damage-sensitive features to detect structural damage. In this paper, a new structural damage identification approach is proposed based on Dempster-Shafer theory and cloud model. Cloud models were created to make uncertainty reasoning in damage structures by modal strain energy and the Inner Product Vector of acceleration. Then the results of the two methods were combined by using the Dempster-Shafer theory. Due to the classical D-S theory involves counter -intuitive behavious when the high conflicting evidences exists, the distance function was introduced to correct the conflict factor and combine the evidences. Moreover, a model of simple beam was created to verify the feasibility and accuracy for the single-damage and the multiple-damage. The effects of noise on damage detection were investigated simultaneously. The results show that the method has strong anti-noise ability and high accuracy.

Fractal dimension based damage identification incorporating multi-task sparse Bayesian learning

“…Once we integrate these damage indication information from various sources into a consistent set, the reliability of damage localization should be improved significantly. Actually, information fusion techniques, including Fuzzy logic inference [20], neural network [21] and Dempster-Shafer evidence theory [22], were studied extensively in the damage identification community in the last decades. In this paper, novel multi-task sparse Bayesian learning framework [23] is employed to fuse the dependent strength of the three damage indication information above, where the relationship between the two fractal dimension indices with the damage localization vector are modeled in the likelihood function and the sparse damage information is incorporated in the automatic relevance determination (ARD) prior.…”