Wind energy is becoming an essential source of power for countries which have the aim to reduce greenhouse gases emission and mitigate the effects of global warming. The Wind Turbines (WTs) installed around the globe is increasing significantly every year. The dramatic increase in wind power has encountered quite a few challenges, among which the major issues are availability and reliability. The unexpected failure in WTs Gearbox (GB) ultimately increases the Operation and Maintenance (O&M) cost. The identification of faults in the earlier stages before it turns to catastrophic damage to other components of WT is crucial. This research deals with the prediction of WT failures by using a Supervisory Control and Data Acquisition (SCADA) system. The main aim is to forecast the temperature of the WTs GB to predict the impending overheating of the GB at an early stage. The earlier prediction will help to optimize the maintenance period and to save maintenance expenses and, even more important, generate warnings in due time to avoid major damages or even technical disasters. In the proposed method we compared six different machine learning (ML) models based on error and accuracy of prediction. The bagging regressor is the best ML model, which results in the mean square error of 0.33 and R of 99.8 on training data. The bagging regressor is then used to predict the fault in the WT GB, which detected the anomalous behavior of WT GB 59 days earlier than the actual failure. This model also detects the extremely unusual behavior of the GB 9 days earlier than a complete failure.

In this work, a highly efficient, molybdenum disulfide (MoS2) based near infrared (NIR) heterojunction photodetector is fabricated on a Si substrate using a cost-effective and simple drop casting method. A non-stoichiometric and inhomogeneous MoS2 layer with a S/Mo ratio of 2.02 is detected using energy dispersive X-ray spectroscopy and field emission scanning electron microscope analysis. Raman shifts are noticed at 382.42 cm-1 and 407.97 cm-1, validating MoS2 thin film growth with a direct bandgap of 2.01 eV. The fabricated n-MoS2/p-Si photodetector is illuminated with a 785 nm laser at different intensities, and demonstrate the ability of the photodetector to work in both regions, the forward biased and reverse biased from above 1.5 V and less than -1.0 V. The highest responsivity, R is calculated to be 0.52 A/W while the detectivity D* is 4.08 x 10^10 Jones for an incident light intensity of 9.57 mW/cm2. The minimum rise and fall times are calculated as 1.77 ms and 1.31 ms for an incident laser power of 9.57 mW/cm^2 and 6.99 mW/cm^2 respectively at a direct current bias voltage of 10 V. The demonstrated results are promising for the low-cost fabrication of a thin MoS2 film for photonics and optoelectronic device applications.

Rhenium Disulfide (ReS2) has evolved as a novel 2D transition-metal dichalcogenide (TMD) material which has promising applications in optoelectronics and photonics because of its distinctive anisotropic attributes. In this review, we emphasize on formulating saturable absorbers (SAs) based on ReS2 to produce Q-switched and mode-locked pulsed lasers of diverse operation wavelengths like 1 μm, 1.5 μm, 2 μm, and 3 μm. We outline ReS2 synthesis techniques and integration platforms concerning solid-state and fiber-type lasers. We discuss the laser performance based on SAs attributes. Lastly, we draw conclusions and outlook by recommending additional improvements for SA devices so as to advance the domain of ultrafast photonic technology.