Condition monitoring (CM) of industrial processes is essential for reducing downtime and increasing productivity through accurate Condition-Based Maintenance (CBM) scheduling. Indeed, advanced intelligent learning systems for Fault Diagnosis (FD) make it possible to effectively isolate and identify the origins of faults. Proven smart industrial infrastructure technology enables FD to be a fully decentralized distributed computing task. To this end, such distribution among different regions/institutions, often subject to so-called data islanding, is limited to privacy, security risks, and industry competition due to the limitation of legal regulations or conflicts of interest. Therefore, Federated Learning (FL) is considered an efficient process of separating data from multiple participants to collaboratively train an intelligent and reliable FD model. As no comprehensive study has been introduced on this subject to date, as far as we know, such a review-based study is urgently needed. Within this scope, our work is devoted to reviewing recent advances in FL applications for process diagnostics, while FD methods, challenges, and future prospects are given special attention.

The green conversion of proton exchange membrane fuel cells (PEMFCs) has received particular attention in both stationary and transportation applications. However, the poor durability of PEMFC represents a major problem that hampers its commercial application since dynamic operating conditions, including physical deterioration, have a serious impact on the cell performance. Under these circumstances, prognosis and health management (PHM) plays an important role in prolonging durability and preventing damage propagation via the accurate planning of a condition-based maintenance (CBM) schedule. In this specific topic, health deterioration modeling with deep learning (DL) is the widely studied representation learning tool due to its adaptation ability to rapid changes in data complexity and drift. In this context, the present paper proposes an investigation of further deeper representations by exposing DL models themselves to recurrent expansion with multiple repeats. Such a recurrent expansion of DL (REDL) allows new, more meaningful representations to be explored by repeatedly using generated feature maps and responses to create new robust models. The proposed REDL, which is designed to be an adaptive learning algorithm, is tested on a PEMFC deterioration dataset and compared to its deep learning baseline version under time series analysis. Using multiple numeric and visual metrics, the results support the REDL learning scheme by showing promising performances.

The clean energy conversion characteristics of proton exchange membrane fuel cells (PEMFCs) have given rise to many applications, particularly in transportation. Unfortunately, the commercial application of PEMFCs is hampered by the early deterioration and low durability of the cells. In this case, accurate real-time condition monitoring plays an important role in extending the lifespan of PEMFCs through accurate planning of maintenance tasks. Accordingly, among the widely used modeling tools such as model-driven and data-driven, machine learning has received much attention and has been extensively studied in the literature. Small-scale machine learning (SML) and Deep Learning (DL) are subcategories of machine learning that have been exploited so far. In this context and since SML usually contains non-expansive approximators, this study was dedicated to improving its feature representations for better predictions. Therefore, a recurrent expansion experiment was conducted for several rounds to investigate a linear regression model under time series prognosis of PEMFCs. The results revealed that the prediction performance of SML tools under stationary conditions could be further improved.