RESUMEN
Predictive maintenance is considered a proactive approach that capitalizes on advanced sensing technologies and data analytics to anticipate potential equipment malfunctions, enabling cost savings and improved operational efficiency. For journal bearings, predictive maintenance assumes critical significance due to the inherent complexity and vital role of these components in mechanical systems. The primary objective of this study is to develop a data-driven methodology for indirectly determining the wear condition by leveraging experimentally collected vibration data. To accomplish this goal, a novel experimental procedure was devised to expedite wear formation on journal bearings. Seventeen bearings were tested and the collected sensor data were employed to evaluate the predictive capabilities of various sensors and mounting configurations. The effects of different downsampling methods and sampling rates on the sensor data were also explored within the framework of feature engineering. The downsampled sensor data were further processed using convolutional autoencoders (CAEs) to extract a latent state vector, which was found to exhibit a strong correlation with the wear state of the bearing. Remarkably, the CAE, trained on unlabeled measurements, demonstrated an impressive performance in wear estimation, achieving an average Pearson coefficient of 91% in four different experimental configurations. In essence, the proposed methodology facilitated an accurate estimation of the wear of the journal bearings, even when working with a limited amount of labeled data.
RESUMEN
Understanding the transmission phenomena of SARS-CoV-2 by virus-laden droplets and aerosols is of paramount importance for controlling the current COVID-19 pandemic. Detailed information about the lifetime and kinematics of airborne droplets of different size is relevant in order to evaluate hygiene measures like wearing masks but also social distancing and ventilation concepts for indoor environments. However, the evaporation process of expiratory droplets and aerosols is not fully understood. Consequently, the main objective of this study is to present evaporation characteristics of saliva droplets. An acoustic levitator is utilized in conjunction with microscopic imaging for recording the temporal evolution of the evaporation of saliva droplets under well-defined ambient conditions. Following the evaporation of the water content, a saliva droplet reaches a final size, which remains stable in the timescale of hours. By investigating numerous droplets of different size, it was found that the final droplet diameter correlates well to 20 % of the initial diameter. This correlation is independent of the ambient conditions for a temperature range from 20 °C to 29 °C and a relative humidity from 6 % to up to 65 %. The experimentally obtained evaporation characteristics are implemented into a numerical model, which is based on one-dimensional droplet kinematics and a rapid mixing evaporation model. By taking into account the evaporation-falling curve as presented by Wells, the significance of the experimental results for predicting the lifetime of saliva droplets and aerosols is demonstrated. The numerical predictions may be used to determine the impact of the droplet size and the ambient conditions on the transmission risks of infectious diseases like COVID-19.