Wind

This work proposes and evaluates a supervised classification framework based on multichannel vibration signals to analyze two systems associated with wind turbines: rotor imbalance in a laboratory-adapted Enair E30Pro wind turbine and structural damage in a jacket-type structure. The methodology compares single-task and multitask learning models using spectral representations obtained from the Fast Fourier Transform (FFT) in log-magnitude format, the Short-Time Fourier Transform (STFT) in log-power format, and the Welch power spectral density (Welch PSD) in log-power format. During the single-task stage, TabNet (Attentive Interpretable Tabular Learning) models, a deep learning architecture designed for tabular data, were independently trained for each system and representation to establish baseline performance levels. Subsequently, a multitask scheme composed of a shared encoder and two task-specific classification heads was implemented: one for the jacket-type structure and another for the rotor. In addition to the original TabNet baselines, a capacity-matched single-task MLP control was evaluated using the same encoder architecture, preprocessing, optimization settings, epoch budget, and cross-validation folds as the multitask model. Relative to the TabNet baselines, the multitask model achieved higher performance in several configurations, particularly for the more challenging rotor task; however, the capacity-matched control showed that these gains cannot be attributed uniquely to multitask parameter sharing because the multitask model did not consistently outperform an equivalently structured single-task network. For the jacket-type structure, all three spectral representations achieved near-perfect classification performance, with Macro-F1 values above 0.99 in both the single-task and multitask settings. For the rotor imbalance problem, the multitask model using Welch PSD log-power achieved a global accuracy of 0.9125 and a Macro-F1 of 0.8909. Negative-control experiments further showed that replacing the auxiliary-task labels with random permutations reduced target-task performance in several configurations, indicating that informative auxiliary supervision influences the shared optimization process, although this effect did not translate into a consistent predictive advantage over the capacity-matched single-task control. The multitask architecture nevertheless provides a parameter-efficient joint formulation: one shared multitask network contains 4,481,354 trainable parameters, compared with 8,958,218 parameters required by two independent capacity-matched single-task networks, corresponding to an approximately 49.97% reduction in total model parameters. Overall, the results support multitask learning as a compact joint modeling strategy for physically different vibration-based classification problems, while indicating that its principal benefit in the present study is architectural efficiency rather than a consistently superior predictive effect attributable to positive cross-task transfer.

Identifying areas for further wind energy investigation requires information on wind resources, accessibility, and land availability. Yet national screening may select similar areas of land while identifying different locations as assumptions change. This study assesses the geographic persistence of wind energy priorities in Yemen and how alternative electricity network maps affect the interpretation of persistent locations. On a common 1 km grid, wind power density at 100 m and road proximity determine priority, while land exclusions determine fractional availability. Cell recurrence is evaluated across 36 spatial preference analyses and a separate 17-setting weight sweep, with complementary resource formulation and processing diagnostics. Changing the road response function leaves the selected area nearly unchanged but yields a cell set Jaccard similarity of 0.722. Under the reference WPD formulation, their strict intersection retains 14,968 cells covering 12,805.42 km² (32.9% of reference top 10% area). Alternative resource formulations also change core membership. For these fixed locations, 20.02% of available land lies within 50 km of mapped historical transmission, compared with 68.61% under modeled GridFinder. Governorate patterns and Socotra’s protected area sensitivity reveal differences obscured by national totals. These findings guide resource, land, and electricity infrastructure verification before project-level assessment.

Wind energy conversion systems based on dual-star induction generators (DSIGs) exhibit nonlinear dynamics and sensitivity to operating-condition variations, which can adversely affect power tracking, DC-link voltage regulation, and power quality. This study proposes a fractional-order backstepping control strategy optimized by the Ant Lion Optimizer (FOBC-ALO) for a DSIG-based wind energy conversion system. The fractional-order formulation provides an additional degree of freedom for shaping the controller response, while the ALO algorithm is employed to optimize the controller gains. The fractional order is selected through a sensitivity analysis, with α = 0.5 providing the most balanced performance among tracking accuracy, transient response, DC-link voltage regulation, and harmonic distortion. The proposed controller was implemented and evaluated in MATLAB 2021/Simulink and compared with a conventional backstepping controller under four simulation scenarios involving variable wind-speed profiles, machine-parameter variations, stepwise wind-speed changes, and operation without maximum power point tracking. The results show that the proposed controller consistently improves the dynamic and power-quality performance of the DSIG-based system. In the first test, the active-power response time was reduced from 1.66 to 1.32 ms, while the current total harmonic distortion (THD) decreased from 1.87% to 1.06%. Under 100% variations in the selected machine parameters, the THD decreased from 5.13% to 2.13%, while the DC-link voltage fluctuation was reduced from 10.18 to 3.02 V. For the stepwise wind-speed test, the proposed controller reduced the active-power response time by 47.99%, the ITAE by 63.70%, the DC-link voltage fluctuation by 71.90%, and the current THD by 48.69%. In the operation without MPPT, the integral of time multiplied by squared error (ITSE), integral of time multiplied by absolute error (ITAE), DC-link voltage ripple, and current THD were reduced by 41.28%, 57.67%, 74.88%, and 46.94%, respectively. Overall, the simulation results indicate that the proposed FOBC-ALO strategy improves reference tracking, transient response, DC-link voltage regulation, and current waveform quality across the investigated operating conditions. The findings provide a simulation-based foundation for subsequent real-time and experimental validation of fractional-order control for DSIG-based wind energy conversion systems.