In this study, we propose a data-driven survival risk analysis approach in support of predictive maintenance management of a large portfolio of industrial assets. The concrete use case considered is a large portfolio of industrial vehicles (trucks). However, the approach is generic (i.e., asset-type agnostic) in nature and can be applied in different industrial contexts. It is able to employ different data sources in the risk analysis workflow, e.g., time series operation data collected via a multitude of sensor measurements combined with tabular data recording the technical specifications of the assets (vehicles). Subsequently, several different risk assessment strategies can be considered: 1) operation-related risk at each time step for any asset computed on the operation data across the whole portfolio; 2) the failure predisposition of each asset determined by its technical specification; 3) hybrid risk analysis, which innovatively combines the different data types to estimate overall risk at any time in the future for any asset. Our validation, conducted on real-world data, demonstrates that the hybrid approach provides a realistic temporal risk assessment during vehicle operation that also reflects adequately the inherent (contextual) risk predisposition of the vehicle due its technical specification. The proposed approach derives diverse survival risk estimations, which are interpretable by design and in this way facilitate both prognostic health monitoring and root cause analysis of the factors impacting vehicles’ risk of failure.

This paper proposes a novel federated learning methodology, called FedRepo, that copes with concept drift issues in a statistically heterogeneous distributed learning environment. The proposed horizontal federated learning methodology, based on random forest (RF), can be used for collaborative training and maintenance of a dynamic repository of federated RF models, each one customized to a group of clients/devices. The clients are grouped together if their performance patterns with respect to the global RF model are similar. The performance of the customized RF global models is continuously monitored during the inference phase and the repository is accordingly adapted to mitigate the detected concept drift. The proposed methodology is studied and evaluated against an electricity consumption forecasting use case. The evaluation results demonstrate clearly that the proposed methodology is able to deal with concept drift issues in an efficient and adequate fashion without compromising the overall performance of the distributed environment.