Impact of Interdependencies: Multi-Component System Perspective toward Predictive Maintenance Based on Machine Learning and XAI

Abstract

Taking the multi-component perspective in Predictive Maintenance (PdM) is one promising approach to improve prediction quality. Therefore, detection and modeling of interdependencies within systems are important, especially as systems become more complex and personalized. However, existing solutions in PdM mostly focus on a single-component perspective, neglecting the dependencies between components, even if interdependencies can be found between most components in the real world. The major reason for this lost opportunity is the challenge of identifying and modeling interdependencies between components. This paper introduces a framework to identify interdependencies and explain their impact on PdM within a Multi-Component System (MCS). The contribution of this approach is two-fold. First, it shows the impact of modeling interdependencies in predictive analytics. Second, it helps to understand which components interact with each other and to which degree they affect the deterioration state of corresponding components. As a result, our approach can identify and explain the existence of interdependencies within components. In particular, we demonstrate that time from last change of component is a valuable feature to quantify interdependencies. Moreover, we show that taking into account the interdependencies provides a statistically significant improvement of f1-score by 7% on average compared to the model where interdependencies are neglected. We expect that our findings will improve maintenance scheduling in the industry while improving prediction models in general.