Prognostics and Health Management of Industrial Assets: Current Progress and Road Ahead

Abstract

Prognostic and Health Management (PHM) systems are some of the main protagonists of the Industry 4.0 revolution. Efficiently detecting whether an industrial component has deviated from its normal operating condition or predicting when a fault will occur are the main challenges these systems aim at addressing. Efficient PHM methods promise to decrease the probability of extreme failure events, thus improving the safety level of industrial machines. Furthermore, they could potentially drastically reduce the often conspicuous costs associated with scheduled maintenance operations. The increasing availability of data and the stunning progress of Machine Learning (ML) and Deep Learning (DL) techniques over the last decade represent two strong motivating factors for the development of data-driven PHM systems. On the other hand, the black-box nature of DL models significantly hinders their level of interpretability, de facto limiting their application to real-world scenarios. In this work, we explore the intersection of Artificial Intelligence (AI) methods and PHM applications. We present a thorough review of existing works both in the contexts of fault diagnosis and fault prognosis, highlighting the benefits and the drawbacks introduced by the adoption of AI techniques. Our goal is to highlight potentially fruitful research directions along with characterizing the main challenges that need to be addressed in order to realize the promises of AI-based PHM systems.

A data-centric approach to the study of system-level prognostics for cyber physical systems: application to safe UAV operations

“…There are a large number of excellent articles within the PHM literature that have led to health management advances that are being deployed today for real-world use-cases [27,28] . However, many of these are applicationspecific methods, when viewed from a larger context of SLP are difficult to generalize across systems or applications [29,30] .…”

Uncertainty-Aware Prognosis via Deep Gaussian Process

“…Over the last few years, different types of DNNs have been developed for RUL prediction, ranging from relatively complex fully-connected networks to Convolutional Neural Networks [29]- [31] and Recurrent Neural Networks [32]- [34]. DL models have shown promising performance in estimating the RUL from sensor data on prognostics benchmark datasets [35], [36] using several different network architectures (see [8] for an extensive review). More sophisticated extensions to the aforementioned standard architectures have also recently been applied to prognosis, including attention mechanisms [37] and capsule neural networks [38].…”

“…While Deep Neural Networks (DNN) have delivered their most prominent achievements in the fields of Computer Vision and Natural Language Processing, recent research works have shown their effective use also for prognostics [7], VOLUME 4, 2016 [8]. DNNs owe a great part of their success to their large representation power and to their capacity of learning sets of hierarchical features across their multilayer architectures directly from raw data.…”

Uncertainty-aware Remaining Useful Life predictor

“…Over the last few years, different types of DNNs have been developed for RUL prediction, ranging from relatively complex fully-connected networks to Convolutional Neural Networks (CNN) [23][24][25] and Recurrent Neural Networks (RNN) [26][27][28]. DL models have shown promising performance in estimating the RUL from sensor data on prognostics benchmark datasets [29,30] using several different network architectures (see [47] for an extensive review). More sophisticated extensions to the aforementioned standard architectures have also recently been applied to prognosis, including attention mechanisms [68] and capsule neural networks [71].…”

“…While Deep Neural Networks (DNN) have delivered their most prominent achievements in the fields of Computer Vision (CV) and Natural Language Processing (NLP), recent research works have shown their effective use also for prognostics [47,70]. DNNs owe a great part of their success to their large representation power and to their capacity of learning sets of hierarchical features across their multilayer architectures directly from raw data.…”