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.

Critical infrastructure, such as water treatment facilities, largely relies on the effective functioning of industrial control systems (ICSs). Due to the wide adoption of high-speed network and digital infrastructure technologies, these systems are now highly interconnected not only to corporate networks but also to the public Internet, mostly for remote control and monitoring purposes. Sophisticated cyber-attacks may take advantage the increased interconnectedness or other security gaps of an ICS and infiltrate the system with devastating consequences to the economy, national security, and even human life. Due to the paramount importance of detecting and isolating these attacks, we propose an unsupervised anomaly detection approach that employs causal inference to construct a robust anomaly score in two phases. First, minimal domain knowledge via causal models helps identify critical interdependencies in the system, while univariate models contribute to individually learn the normal behavior of the system’s components. In the final phase, we employ the extreme studentized deviate (ESD) on the computed score to detect attacks and to exclude any irrelevant sensor signals. Our approach is validated on the widely used Secure Water Treatment (SWaT) benchmark, and it exhibits the highest F1 score with zero false alarms, which is extremely important for real-world deployment.

In a dynamic production processes, mechanical degradation poses a significant challenge, impacting product quality and process efficiency. This paper explores a novel approach for monitoring degradation in the context of viscose fiber production, a highly dynamic manufacturing process. Using causal discovery techniques, our method allows domain experts to incorporate background knowledge into the creation of causal graphs. Further, it enhances the interpretability and increases the ability to identify potential problems via changes in causal relations over time. The case study employs a comprehensive analysis of the viscose fiber production process within a prominent textile industry, emphasizing the advantages of causal discovery for monitoring degradation. The results are compared with state-of-the-art methods, which are not considered to be interpretable, specifically LSTM-based autoencoder, UnSupervised Anomaly Detection on Multivariate Time Series (USAD), and Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data (TranAD), showcasing the alignment and validation of our approach. This paper provides valuable information on degradation monitoring strategies, demonstrating the efficacy of causal discovery in dynamic manufacturing environments. The findings contribute to the evolving landscape of process optimization and quality control.