Wind turbines generate clean and renewable energy for the international market. The most ‎‎important aspect of wind turbine maintenance is reducing failures, downtime, and operating and maintenance expenses. ‎This study aims to detect multiple faults exhibited by wind turbine blades; failures such as cracks (tip crack, mid-span crack, and crack ‎near the root) were observed in the blades at different locations. The research suggests a new approach, incorporating vibration signals and machine learning techniques to identify various failures in wind turbine blades. The technology of ranking features such as ReliefF algorithms, chi-squares, and information gains was adopted to discuss a method framework to diagnose several problems in wind turbine blades, such as cracks in different locations. The k-nearest neighbors (KNNs), support vector machines, and random forests are used to classify data based on measured vibration signals. The eight main time-domain features are calculated from the vibration signals. The proposed methodology was validated using four databases. The results showed good classification accuracy in four databases, with at least three non-conventional features in each database’s top nine features of the three classification techniques. The results also showed that when the ReliefF selection algorithm is applied with the KNN classification algorithm, it generates the highest classification accuracy under all failure conditions, and the value is 97%. Finally, the performance of the proposed classification model is compared with other machine learning classification models, and a promising result is obtained. ‎

The incorporation of fiber reinforcements into polymer matrices has emerged as an effective strategy to enhance the mechanical properties of composites. This study investigated the tensile and fracture behavior of 3D-printed polylactic acid (PLA) composites reinforced with chopped carbon fibers (CCFs) through experimental characterization and finite element analysis (FEA). Composite samples with varying CCF orientations (0°, 0°/90°, +45°/−45°, and 0°/+45°/−45°/90°) were fabricated via fused filament fabrication (FFF) and subjected to tensile and single-edge notched bend (SENB) tests. The experimental results revealed a significant improvement in tensile strength, elastic modulus, and fracture toughness compared to unreinforced PLA. The 0°/+45°/90° orientation exhibited a 3.6% increase in tensile strength, while the +45°/−45° orientation displayed a 29.9% enhancement in elastic modulus and a 29.9% improvement in fracture toughness (259.12 MPa) relative to neat PLA (199.34 MPa√m). An inverse correlation between tensile strength and fracture toughness was observed, attributed to mechanisms such as crack deflection, fiber bridging, and fiber pull-out facilitated by multi-directional fiber orientations. FEA simulations incorporating a transversely isotropic material model and the J-integral approach were conducted using Abaqus, accurately predicting fracture toughness trends with a maximum discrepancy of 8% compared to experimental data. Fractographic analysis elucidated the strengthening mechanisms, highlighting the potential of tailoring CCF orientation to optimize mechanical performance for structural applications.

The increasing prevalence of unmanned aerial vehicles (UAVs) across various fields requires the development of advanced fault detection and diagnostic (FDD) frameworks to prevent the severe consequences of undetected sensor and actuator failures. This review investigates the wide spectrum of FDD methodologies for UAVs, focusing on the paramount role of sophisticated yet intelligent systems in safeguarding operational integrity, particularly in near-human environments. An analysis of 32 seminal publications from well-recognized databases presents a trend towards converging signal processing and machine learning techniques using UAV specific fault detection keywords. This analysis underscores the trend of data-driven models capable of performing real-time diagnostics. The authors increase interest in hybrid methodologies that correlate the precision of signal processing and the adaptive nature of machine learning. These approaches aim to gain fault detection accuracy and achieve better prognostic capabilities. By deconstructing the strengths and weaknesses of various methods, this analysis concludes with the need for further research into upcoming new challenges. The review focuses on the investigation of synergistic strategies and encourages interdisciplinary collaboration for advancements in FDD methods. These initiatives will enhance UAV safety and reliability across a wide range of operational contexts.

Integration of Machine Learning (ML) and Finite Element Analysis (FEA) for Predicting the Failure Modes of a Small Horizontal Composite Blade

Statistically Optimal Vibration Feature Selection for Fault Diagnosis in Wind Turbine Blade