A prognostics approach based on the evolution of damage precursors using dynamic Bayesian networks

Abstract

During the lifetime of a component, microstructural changes emerge at its material level and evolve through time. Classical empirical degradation models (e.g. Paris Law in fatigue crack growth) are usually established based on monitoring and estimating well-known direct damage indicators such as crack size. However, by the time the usual inspection techniques efficiently identify such damage indicators, most of the life of the component would have been expended, and usually it would be too late to save the component. Therefore, it is important to detect damage at the earliest possible time. This article presents a new structural health monitoring and damage prognostics framework based on evolution of damage precursors representing the indirect damage indicators, when conventional direct damage indicator, such as a crack, is unobservable, inaccessible, or difficult to measure. Dynamic Bayesian network is employed to represent all the related variables as well as their causal or correlation relationships. Since the degradation model based on damage precursor evolution is not fully recognized, the methodology needs to be capable of online-learning the degradation process as well as estimating the damage state. Therefore, the joint particle filtering technique is implemented as an inference method inside the dynamic Bayesian network to assess both model parameters and damage states simultaneously. The proposed framework allows the integration of any related sources of information in order to reduce the inherent uncertainties. Incorporating different types of evidences in dynamic Bayesian network entails advance techniques to identify and formulate the possible interaction between potentially nonhomogenous variables. This article uses the support vector regression in order to define generally unknown nonparametric and nonlinear correlation between the input variables. The methodology is successfully applied to damage estimation and prediction of crack initiation in a metallic alloy under fatigue. The proposed framework is intended to be general and comprehensive so that it can be implemented in different applications.Chilean National Fund for Scientific and Technological Development (Fondecyt) 116049

Fully Adaptive Particle Filtering Algorithm for Damage Diagnosis and Prognosis

“…Some examples can be found in [ 4 , 11 , 32 , 33 , 34 ]. This leads to a very basic and simple linear measurement model, as follows: The second group can be considered as the cases when “ is NOT necessarily the same quantity as ”; for example in [ 16 , 35 , 36 , 37 ]. Therefore, has a different nature and needs to be related to the hidden variable through some physical or data-driven model: …”

“…The second group can be considered as the cases when “ is NOT necessarily the same quantity as ”; for example in [ 16 , 35 , 36 , 37 ]. Therefore, has a different nature and needs to be related to the hidden variable through some physical or data-driven model: …”

Deep transfer learning for rolling bearing fault diagnosis under variable operating conditions

“…3 Traditional machine learning (ML) algorithms have been widely employed in machine fault diagnosis, including artificial neural network (ANN), support vector machine (SVM), Bayesian network, and hidden Markov model (HMM). [4][5][6][7] Nevertheless, those traditional methods require extensive domain expertise and prior knowledge, and the feature extraction is also limited in existing features or evaluation criteria. Thus, it is difficult to build a suitable model for complex fault diagnosis under variable operating conditions.…”

Hybrid residual fatigue life prediction approach for gear based on Paris law and particle filter with prior crack growth information

“…The Paris law is a widely used model-based prognostic approach, and it has been proven that gear crack-growth rates follow it [4]. In addition, fatigue life prediction models in most literature sources are based on the traditional Paris law and are usually established based on monitoring and estimation of well-known direct damage indicators such as a crack size [5]. Therefore, the fatigue life prediction based on the Paris law has received considerable attention in recent years [6][7][8][9][10], and it has been applied to a range of applications, including axial flow compressors [1], girth gear-pinion assembly [11], ball bearings [2], and interfacial cracked plate [12].…”

“…However, it is different to realize the parameters when it comes to nonlinear situation. Particle filter is widely used in the engineering, and it is especially suitable for processing the nonlinear and non-Gaussian systems [5,17,18]. Hence, we take the particle filtering technique as an inference method inside the dynamic Bayesian network to assess both model parameters and damage states simultaneously.…”