Bearings are vital components in rotating machinery. Undetected bearing faults may result not only in financial loss, but also in the loss of lives. Hence, there exists an abundance of studies working on the early detection of bearing faults. The rising use of deep learning in recent years increased the number of imaging types/neural network architectures used for bearing fault classification, making it challenging to choose the most suitable 2-D imaging method and neural network. This study aims to address this challenge, by sharing the results of the training of eighteen imaging methods with four different networks using the same vibration data and training metrics. To further strengthen the results, the validation dataset size was taken as five times the training dataset size. The best results obtained is 99.89% accuracy by using Scattergram Filter Bank 1 as the image input, and ResNet-50 as the network for training. Prior to our work, Scattergram images have never been used for bearing fault classification. Ten out of 72 methods used in this work resulted in accuracies higher than 99.5%.

Digital twins, virtual representations of real-life physical objects or processes, are becoming widely used in many different industrial sectors. One of the main uses of digital twins is predictive maintenance, and these technologies are being adapted to various new applications and datatypes in many industrial processes. The aim of this study was to propose a methodology to generate synthetic vibration data using a digital twin model and a predictive maintenance workflow, consisting of preprocessing, feature engineering, and classification model training, to classify faulty and healthy vibration data for state estimation. To assess the success of the proposed workflow, the mentioned steps were applied to a publicly available vibration dataset and the synthetic data from the digital twin, using five different state-of-the-art classification algorithms. For several of the classification algorithms, the accuracy result for the classification of healthy and faulty data achieved on the public dataset reached approximately 86%, and on the synthetic data, approximately 98%. These results showed the great potential for the proposed methodology, and future work in the area.

Being a cornerstone of Industry 4.0, Asset Administration Shell (AAS) enables seamless integration and interaction among the physical and digital worlds. There are multiple different tools and technologies available for implementing AAS. The purpose of this study is to support the tool and technology selection decision of AAS modelers and implementers. For that purpose, we conducted a literature survey and identified four active tools, and in the study, we included all of them: AASX server, Eclipse BaSyx, FA³ST service, and NOVAAS. Using a comprehensive criteria list, we conducted a thorough comparison of the selected technologies. The comparison was made in two steps: first for initial learning exercises and second for a real case study where digital twins belong to real assets in a facility belonging to the petrochemical industry. Among the evaluated tools, Eclipse BaSyx demonstrated superior performance compared to the other three tools investigated in this study. Future research will focus on incorporating machine learning (ML) and deep learning (DL) models associated with the assets, leveraging datasets generated by the sensors installed on the system.