A Systematic Literature Review on Transfer Learning for Predictive Maintenance in Industry 4.0

Abstract

The advent of Industry 4.0 has resulted in the widespread usage of novel paradigms and digital technologies within industrial production and manufacturing systems. The objective of making industrial operations monitoring easier also implied the usage of more effective data-driven predictive maintenance approaches, including those based on machine learning. Although those approaches are becoming increasingly popular, most of the traditional machine learning and deep learning algorithms experience the following three major challenges: 1) lack of training data (especially faulty data), 2) incompatible computation power, and 3) discrepancy in data distribution. A new data-driven technique, such as transfer learning, can be developed to overcome the issues related to traditional machine learning and deep learning for predictive maintenance. Motivated by the recent big interest towards transfer learning within computer science and artificial intelligence, in this paper we provide a systematic literature review addressing related research with a focus on predictive maintenance. The review aims to define transfer learning in the context of predictive maintenance by introducing a specific taxonomy based on relevant perspectives. We also discuss current advances, challenges, open-source datasets, and future directions of transfer learning applications in predictive maintenance from both theoretical and practical viewpoints.

Cross-Condition Fault Diagnosis of an Aircraft Environmental Control System (ECS) by Transfer Learning

“…Among the three major categories of TL approach in fault diagnosis, instance-based, feature-based, and parameter-based TL, the feature-based TL is determined to be the optimal approach for the problem of interest. The instance-based approach, which reweighs the source domain instances and uses them as auxiliary datasets for target domain problems, is not ideal, because identical conditional distribution is assumed for source and target domain [22]. The parameter-based TL, which reuses hyperparameters in pretrained models from source domain in target domain, is not chosen, since this approach may fail at significant distribution discrepancy [22].…”

“…The instance-based approach, which reweighs the source domain instances and uses them as auxiliary datasets for target domain problems, is not ideal, because identical conditional distribution is assumed for source and target domain [22]. The parameter-based TL, which reuses hyperparameters in pretrained models from source domain in target domain, is not chosen, since this approach may fail at significant distribution discrepancy [22].…”

Advancing maintenance, monitoring, and control techniques for the optimization of power electronic systems

“…This approach involves analyzing historical performance data to identify patterns and trends that can be used to forecast future behavior. Time-series models such as autoregressive integrated moving average (ARIMA) and exponential smoothing are widely used for time-series forecasting tasks [3]. In addition to historical performance data, predictive models also incorporate information about operating conditions, environmental factors, and maintenance history to improve their accuracy and robustness.…”

Rolling Element Bearing Degradation Prediction Using Dynamic Model and an Improved Adversarial Domain Adaptation Approach

“…To tackle these problems, domain adaptation has been proposed [23,24], whose principle is to learn mutual features between the labelled source domain and the unlabelled target domain, as a result, the degradation knowledge can be transferred from one domain to another. Domain adaptation include discrepancy metric-based domain adaptation and adversarial training-based domain adaptation [25].…”