A Literature Review on the Development and Creation of Digital Twins, Cyber-Physical Systems, and Product-Service Systems.

Digital Twins offer vast potential, yet many companies, particularly small and medium-sized enterprises, hesitate to implement them. This hesitation stems partly from the challenges posed by the interdisciplinary nature of creating Digital Twins. To address these challenges, this paper explores systematic approaches for the development and creation of Digital Twins, drawing on relevant methods and approaches presented in the literature. Conducting a systematic literature review, we delve into the development of Digital Twins while also considering analogous concepts, such as Cyber-Physical Systems and Product-Service Systems. The compiled literature is categorised into three main sections: holistic approaches, architecture, and models. Each category encompasses various subcategories, all of which are detailed in this paper. Through this comprehensive review, we discuss the findings and identify research gaps, shedding light on the current state of knowledge in the field of Digital Twin development. This paper aims to provide valuable insights for practitioners and researchers alike, guiding them in navigating the complexities associated with the implementation of Digital Twins.

Investigation of Feature Engineering Methods for Domain-Knowledge-Assisted Bearing Fault Diagnosis.

The engineering challenge of rolling bearing condition monitoring has led to a large number of method developments over the past few years. Most commonly, vibration measurement data are used for fault diagnosis using machine learning algorithms. In current research, purely data-driven deep learning methods are becoming increasingly popular, aiming for accurate predictions of bearing faults without requiring bearing-specific domain knowledge. Opposing this trend in popularity, the present paper takes a more traditional approach, incorporating domain knowledge by evaluating a variety of feature engineering methods in combination with a random forest classifier. For a comprehensive feature engineering study, a total of 42 mathematical feature formulas are combined with the preprocessing methods of envelope analysis, empirical mode decomposition, wavelet transforms, and frequency band separations. While each single processing method and feature formula is known from the literature, the presented paper contributes to the body of knowledge by investigating novel series connections of processing methods and feature formulas. Using the CWRU bearing fault data for performance evaluation, feature calculation based on the processing method of frequency band separation leads to particularly high prediction accuracies, while at the same time being very efficient in terms of low computational effort. Additionally, in comparison with deep learning approaches, the proposed feature engineering method provides excellent accuracies and enables explainability.