Towards an extension of Fault Trees in the Predictive Maintenance Scenario

TL;DR

The paper addresses the challenge of applying Fault Tree Analysis to Predictive Maintenance in complex CPS by introducing the Predictive Fault Tree (pdft) formalism, a hybrid model-based/data-driven framework that represents components, ports, dynamics, and probabilistic transitions with a global alert function $\Phi$. The authors propose a workflow that integrates mb and dd techniques—such as Time Series Analysis, Association Rules Learning, and Process Mining—to refine and analyze pdft models, and outline a pathway to translate pdft models into Generalised Stochastic Petri Nets ($GSPN$) for rigorous analysis. Key contributions include the formal pdft definition $<\mathcal{C}, \mathcal{E}, \mathcal{D}, \epsilon, \Phi>$, a concrete example illustrating dynamics and thresholds, and a use-case-driven mapping of data-driven methods to pdft elements. The work aims to improve realism, interpretability, and data efficiency in predictive maintenance, with practical impact for CPS like railways and other critical infrastructures, by enabling flexible, explainable fault analysis under evolving environmental conditions.

Abstract

One of the most appreciated features of Fault Trees (FTs) is their simplicity, making them fit into industrial processes. As such processes evolve in time, considering new aspects of large modern systems, modelling techniques based on FTs have adapted to these needs. This paper proposes an extension of FTs to take into account the problem of Predictive Maintenance, one of the challenges of the modern dependability field of study. The paper sketches the Predictive Fault Tree language and proposes some use cases to support their modelling and analysis in concrete industrial settings.

Figures (2)

• Figure 1: A sample model and its notation
• Figure 2: An integrated mb-dd approach