Degradation model constructed with the aid of dynamic Bayesian networks

Abstract

This paper develops a generic degradation model based on Dynamic Bayesian Networks (DBN) which predicts the condition of a technical system. Besides handling bi-directional reasoning, a major benefit of this degradation model using a DBN is its ability to adequately model stochastic processes as well as Markov chains. We will assume that the behavior of the degradation can be represented as a P–F-curve (also called degradation or life curve). The model developed here is able to combine information from expert knowledge, any kind of sensor and operating data as well as information from the machine operator. Using the Bayesian approach, uncertain knowledge can be handled appropriately. Thus it is even possible to take into account the environment and stress under which the component or system is operating. Hence, it is possible to detect potential failures at an early stage and initiate appropriate remedy and repair strategies prior to catastrophic failure

Optimization tools applied to physical asset maintenance management: state of the art

“…One tool within the Artificial Intelligence family is Bayesian Networks (BN). These models have different applications for diagnosis, classification and decision making, providing relevant information on how the variables under study are related [63]. They contribute to the improvement of modeling, quantification and analysis of human reliability by taking into account performance factors including complexity, stress, experience, training, work procedures, ergonomics and equipment-related factors as the most significant [59].…”

“…They contribute to the improvement of modeling, quantification and analysis of human reliability by taking into account performance factors including complexity, stress, experience, training, work procedures, ergonomics and equipment-related factors as the most significant [59]. The P-F interval, potential failure -functional failure, is implemented as a dynamic Bayesian network allowing to improve the reliability of physical assets [63]. The P-F interval will define how often the condition tasks should be performed on the asset.…”

Adopting machine learning and condition monitoring P-F curves in determining and prioritizing high-value assets for life extension

“…The approach can be extended to offshore wind energy applications but with more stringent detectability and efficiency parameters due to the logistical complexities of maintaining offshore assets. Lorenzoni et al, (2017) modeled the degradation of components using Dynamic Bayesian Networks, with the P-F curve representing the degradation pattern which was modeled as a reversed exponential function. The characteristic of the P-F curve in the study was susceptible to maintenance activities as well as operating conditions, thus factoring these uncertainties in to derive the health state of equipment.…”

Degradation processes modelled with Dynamic Bayesian Networks

“…7 represent random variables with a finite number of states. For a detailed description thereof refer to [17]. The degradation model consists of four different main parts: The hatched nodes in fig.…”