The increasing application of plain bearings in various industries, especially under challenging conditions like thin lubricating films and high temperatures, necessitates effective monitoring to prevent failures and ensure reliable performance. While sensor-based monitoring incurs significant costs and complex installation due to physical sensors and data acquisition systems, model-based tracking offers a more cost-effective alternative. Model-based monitoring relies on mathematical or physics-based models to estimate system behaviour, reducing the need for extensive sensor data. However, reliable results depend on real-time capable and precise simulation models. Conventional real-time modelling techniques, including analytical calculations, empirical formulas, and data-driven methods, exhibit significant limitations in real-world applications. Analytical methods often have a restricted range of applicability and do not match the accuracy of numerical methods. Meanwhile, data-driven approaches rely heavily on the quality and quantity of training data and are inherently constrained to their training domain. Recently, Physics-Informed Neural Networks (PINNs) have emerged as a promising solution for model-based monitoring to capture complex system behaviour. This approach combines physical modelling with data-driven learning, allowing for better generalisation beyond the training domain while reducing reliance on extensive data. Thus, this study presents an approach for load monitoring in radial plain bearings using PINNs. It extends the application of PINNs by relying solely on simple sensor inputs, such as radial load and rotational speed, to predict the hydrodynamic pressure and oil film thickness distribution under varying stationary conditions. The real-time model is trained, validated, and evaluated within and beyond the training domain using elastohydrodynamic simulation results. The developed real-time model enables load monitoring in plain bearings by identifying critical hydrodynamic pressure and oil film thickness values using readily available speed and load sensor data under varying stationary conditions.
As global wind capacity expands, reducing operations and maintenance costs is critical to lowering the levelized cost of energy. This paper explores the state of the art in condition monitoring and prognostic strategies for wind turbine drivetrains, which are among the most failure-prone and maintenance-intensive subsystems. Current diagnostic methodologies are evaluated, covering supervisory control and data acquisition (SCADA) data, high-frequency vibration and acoustic analysis, machine learning and digital twin frameworks. Finally, practical challenges are identified that limit wide-scale industrial adoption, in order to guide future research and industrial efforts.
Climate change has led to new shipping routes in polar waters, increasing touristic and commercial traffic in these regions. Sequentially, collisions between ship propellers and sea ice have become more frequent. Such collisions subject the propellers to extreme dynamic loads, which are transferred through the propeller shaft to the sliding stern tube bearings, particularly the bearing mounted next to the propeller (aft bearing). These collision loads have been linked to indications of fatigue and wear in sliding bearings. To determine whether these loads contribute to the increasing wear and fatigue damage in bearings, it’s essential to investigate their impact on contact conditions and stress concentration in the bearing. While recent research on stern tube bearing damage has focused on wear, the investigation of fatigue damage remains unexplored. This study aims to assess the impact of ice-induced loads on the remaining fatigue-life of the aft bearing using the research vessel SA Agulhas II as a case study. For this purpose, four design ice load cases and five field-measured ice load cases are used. The impact of ice-induced loads on the local stress tensors are obtained through multi-body and finite element simulations incorporating elastohydrodynamic effects, followed by the calculation of the DANG VAN’s equivalent stress. This is followed by assessing the partial damage from a single cycle of ice-induced load on the aft bearing using the Palmgren-Miner method. Finally, the remaining fatigue-life is determined based on the calculated damage from a single cycle of ice-induced loads. This represents the remaining number of load cycles until damage occurs, indicating the impact of ice-induced loads on fatigue risk.
Increasing ship traffic in ice-covered waters leads to more frequent collisions between ship propellers and sea ice which causes extreme impulse loads on the propeller. Theses loads are transferred through the propeller shaft to the sliding bearings of the stern tube, especially, the aft stern tube bearings. Extreme bearing loads can lead to mixed-friction regimes which cause wear in the bearings and eventually results in a failure of the entire propulsion system. The effect of ice-induced loads on the contact conditions in the sliding bearings is widely unknown. Thus, a study of the influence of these loads on the contact conditions and wear behavior in stern tube bearings resulting from observed sea ice conditions and operating conditions of the ship is necessary. This paper aims to investigate the influence of ice collision loads on the contact conditions in the bearings of the stern tube of the research vessel SA Agulhas II. For this purpose, an elastohydrodynamic simulation and a multibody simulation based on field measurements were performed. As a result, this paper identifies the operating condition thresholds (i.e. propeller torque and rotational speed) during propeller-ice collisions that cause mixed-friction conditions in the bearings. On the basis of these conditions, a risk map is generated to assess the actual wear risk by including the frequency of occurrence of the corresponding mixed-friction condition over the duration of a voyage.
As wind energy scales up to meet global decarbonization and energy security goals, reducing the LCoE has become essential, particularly through improvements in O&M. This positioning paper explores the state-of-the-art in condition monitoring for wind turbines. It focuses on drivetrain components, which are among the most failure-prone and maintenance-intensive subsystems. It examines current diagnostic and prognostic strategies using SCADA data, vibration and acoustic analysis, and digital twin frameworks, alongside emerging techniques in machine learning, signal processing, and hybrid modelling. The paper also identifies key challenges, including data availability, labelling, standardization, and the gap between academic research and industrial adoption. This work aims to guide future research and industrial efforts in making wind energy more reliable, predictable, and cost-efficient.