In the field of predictive maintenance (PdM), machine learning (ML) has gained importance over the last years. Accompanying this development, an increasing number of papers use non-interpretable ML to address PdM problems. While ML has achieved unprecedented performance in recent years, the lack of model explainability or interpretability may manifest itself in a lack of trust. The interpretability of ML models is researched under the terms explainable AI (XAI) and interpretable ML. In this paper, we review publications addressing PdM problems which are motivated by model interpretability. This comprises intrinsically interpretable models and post-hoc explanations. We identify challenges of interpretable ML for PdM, including (1) evaluation of interpretability, (2) the observation that explanation methods explaining black box models may show black box behavior themselves, (3) non-consistent use of terminology, (4) a lack of research for time series data, (5) coverage of explanations, and finally (6) the inclusion of domain knowledge,

Machine learning, with its advances in deep learning has shown great potential in analyzing time series. In many scenarios, however, additional information that can potentially improve the predictions is available. This is crucial for data that arise from e. g., sensor networks that contain information about sensor locations. Then, such spatial information can be exploited by modeling it via graph structures, along with the sequential (time series) information. Recent advances in adapting deep learning to graphs have shown potential in various tasks. However, these methods have not been adapted for time series tasks to a great extent. Most attempts have essentially consolidated around time series forecasting with small sequence lengths. Generally, these architectures are not well suited for regression or classification tasks where the value to be predicted is not strictly depending on the most recent values, but rather on the whole length of the time series. We propose TISER-GCN, a novel graph neural network architecture for processing, in particular, these long time series in a multivariate regression task. Our proposed model is tested on two seismic datasets containing earthquake waveforms, where the goal is to predict maximum intensity measurements of ground shaking at each seismic station. Our findings demonstrate promising results of our approach—with an average MSE reduction of 16.3%—compared to the best performing baselines. In addition, our approach matches the baseline scores by needing only half the input size. The results are discussed in depth with an additional ablation study.

The growing availability of multirelational data gives rise to an opportunity for novel characterization of complex real-world relations, supporting the proliferation of diverse network models such as Attributed Graphs, Heterogeneous Networks, Multilayer Networks, Temporal Networks, Location-aware Networks, Knowledge Networks, Probabilistic Networks, and many other task-driven and data-driven models. In this paper, we propose an overview of these models and their main applications, described under the common denomination of Feature-rich Networks, i. e. models where the expressive power of the network topology is enhanced by exposing one or more peculiar features. The aim is also to sketch a scenario that can inspire the design of novel feature-rich network models, which in turn can support innovative methods able to exploit the full potential of mining complex network structures in domain-specific applications.

The growing number of applications of machine learning and data mining in many domains—from agriculture to business, education, industrial manufacturing, and medicine—gave rise to new requirements for how to inspect and control the learned models. The research domain of explainable artificial intelligence (XAI) has been newly established with a strong focus on methods being applied post-hoc on black-box models. As an alternative, the use of interpretable machine learning methods has been considered—where the learned models are white-box ones. Black-box models can be characterized as representing implicit knowledge—typically resulting from statistical and neural approaches of machine learning, while white-box models are explicit representations of knowledge—typically resulting from rule-learning approaches. In this introduction to the special issue on ‘Explainable and Interpretable Machine Learning and Data Mining’ we propose to bring together both perspectives, pointing out commonalities and discussing possibilities to integrate them.

Complex networks lend themselves for the modeling of multidimensional data, such as relational and/or temporal data. In particular, when such complex data and their inherent relationships need to be formalized, complex network modeling and its resulting graph representations enable a wide range of powerful options. In this paper, we target this—connected to specific machine learning approaches on graphs for Structural Health Monitoring (SHM) from an analysis and predictive (maintenance) perspective. Specifically, we present a framework based on Complex Network Modeling, integrating Graph Signal Processing (GSP) and Graph Neural Network (GNN) approaches. We demonstrate this framework in our targeted application domain of SHM. In particular, we focus on a prominent real-world SHM use case, i. e., modeling and analyzing sensor data (strain, vibration) of a large bridge in the Netherlands. In our experiments, we show that GSP enables the identification of the most important sensors, for which we investigate a set of search and optimization approaches. Furthermore, GSP enables the detection of specific graph signal patterns (i. e., mode shapes), capturing physical functional properties of the sensors in the applied complex network. In addition, we show the efficacy of applying GNNs for strain prediction utilizing this kind of sensor data.

Graph neural networks (GNNs) haven proven to be an indispensable approach in modeling complex data, in particular spatial temporal data, e.g., relating to sensor data given as time series with according spatial information. Although GNNs provide powerful modeling capabilities on such kind of data, they require adequate input data in terms of both signal and the underlying graph structures. However, typically the according graphs are not automatically available or even predefined, such that typically an ad hoc graph representation needs to be constructed. However, often the construction of the underlying graph structure is given insufficient attention. Therefore, this paper performs an in-depth analysis of several methods for constructing graphs from a set of sensors attributed with spatial information, i.e., geographical coordinates, or using their respective attached signal data. We apply a diverse set of standard methods for estimating groups and similarities between graph nodes as location-based as well as signal-driven approaches on multiple benchmark datasets for evaluation and assessment. Here, for both areas, we specifically include distance-based, clustering-based, as well as correlation-based approaches for estimating the relationships between nodes for subsequent graph construction. In addition, we consider two different GNN approaches, i.e., regression and forecasting in order to enable a broader experimental assessment. Typically, no predefined graph is given, such that (ad hoc) graph creation is necessary. Here, our results indicate the criticality of factoring in the crucial step of graph construction into GNN-based research on spatial temporal data. Overall, in our experimentation no single approach for graph construction emerged as a clear winner. However, in our analysis we are able to provide specific indications based on the obtained results, for a specific class of methods. Collectively, the findings highlight the need for researchers to carefully consider graph construction when employing GNNs in the analysis of spatial temporal data.