Search

The increasing complexity of modern mechanical systems, especially rotating machinery, demands effective condition monitoring techniques, particularly deep learning, to predict potential failures in a timely manner and enable preventative maintenance strategies. Health monitoring data analysis, a widely used approach, faces challenges due to data randomness and interpretation difficulties, highlighting the importance of robust data quality analysis for reliable monitoring. This paper presents a two-part approach to address these challenges. The first part focuses on comprehensive data preprocessing using only feature scaling and selection via random forest (RF) algorithm, streamlining the process by minimizing human intervention while managing data complexity. The second part introduces a Recurrent Expansion Network (RexNet) composed of multiple layers built on recursive expansion theories from multi-model deep learning. Unlike traditional Rex architectures, this unified framework allows fine tuning of RexNet hyperparameters, simplifying their application. By combining data quality analysis with RexNet, this methodology explores multi-model behaviors and deeper interactions between dependent (e.g., health and condition indicators) and independent variables (e.g., Remaining Useful Life (RUL)), offering richer insights than conventional methods. Both RF and RexNet undergo hyperparameter optimization using Bayesian methods under variability reduction (i.e., standard deviation) of residuals, allowing the algorithms to reach optimal solutions and enabling fair comparisons with state-of-the-art approaches. Applied to high-speed bearings using a large wind turbine dataset, this approach achieves a coefficient of determination of 0.9504, enhancing RUL prediction. This allows for more precise maintenance scheduling from imperfect predictions, reducing downtime and operational costs while improving system reliability under varying conditions. [ABSTRACT FROM AUTHOR]

In this work, we propose a novel alternative design technique based on combined SCAPS numerical simulations and Machine Learning (ML) computation to improve the photocurrent performances for efficient eco-friendly optoelectronic applications. In this context, a new SnS absorber structure based on introducing gold (Au) nanoparticles (NPs) is proposed. It is revealed that the proposed design framework can predict the best spatial distribution of Au NPs, allowing for the enhanced optical behavior of SnS absorber film. This can pave the way for the optoelectronic systems designers to identify the geometry and the appropriate material for each layer of the device. Moreover, the results of the proposed SnS-based structure offer an innovative approach for the elaboration of eco-friendly, high-efficiency thin-film optoelectronics devices that is more promising than the previously reported designing techniques. [ABSTRACT FROM AUTHOR]

The effects of oxygen concentration and growth technique during the deposition process on the electrical properties of tin oxide alloy (SnOx) should be investigated for developing new eco-friendly photosensors and photovoltaic devices. The present work aims to predict the electrical key governing parameters throughout the device developing processes such as the Energy level values and band-gap energy as function of the injected oxygen concentrations. For realization, over 100 data points were collected by modeling the effect of oxygen contents on the SnOx electrical properties using Density Function Theory (DFT). Through extensive Machine Learning (ML) analysis, the impact of the oxygen concentration on the electrical properties and the material type is well predicted, where the applied ML prediction model for band-gap energy showed a good correlation between predicted values and the calculated ones using DFT computations. It is revealed that the combined DFT-ML-based approach can be a powerful tool to study and accelerate the developing of new highly efficient materials for microelectronic applications. [ABSTRACT FROM AUTHOR]

In this paper, the impact of the surface-textured front glass on the absorption of TiO2/glass thin-film ultraviolet (UV) photodetector is investigated, in order to achieve the dual role of increasing the scattering of UV-light as well as reducing the refracting UV-light in the glass. The efficient control of these phenomena may lead to more electric field confinement and UV-light trapping in TiO2 absorber layer. Moreover, semianalytical modeling combined with particle swarm optimization is carried out for studying and enhancing the metal–semiconductor–metal photodetector optical and electrical performances. The results obtained from our semianalytical investigation are validated by comparison with the experimental data. It is found that the absorbance increases significantly by about 51% in optimized design over the planar structure, which is expected to improve the photodetector figures of merit. In this context, photodetector with optimized grooves texturization exhibits a 341% improvement, in terms of responsivity, in comparison with the planar structure and 275% improvement with respect to the textured device without optimization. The obtained results make the proposed design methodology a promising alternative for high-performance optoelectronic applications. [ABSTRACT FROM PUBLISHER]